├── .gitattributes
├── .gitignore
├── LICENSE
├── README.md
├── Week1
    ├── ClickHouse
    │   └── docker-compose.yml
    ├── Postgres
    │   ├── container-data
    │   │   └── postgres
    │   │   │   └── init.sql
    │   └── docker-compose.yaml
    ├── employee.png
    ├── help.txt
    └── practice.sql
├── Week2
    ├── docker-hadoop
    │   ├── docker-compose.yml
    │   ├── hadoop.env
    │   ├── init4win7.bat
    │   └── tmp
    │   │   ├── data
    │   │       ├── checkdata.txt
    │   │       ├── checkdata2.txt
    │   │       ├── checkdata3.txt
    │   │       ├── checkdata4.txt
    │   │       └── checkdata5.txt
    │   │   ├── init
    │   │       └── init.sh
    │   │   ├── input
    │   │       ├── input1.txt
    │   │       └── input2.txt
    │   │   └── job
    │   │       └── mr-wordcount.jar
    └── help.txt
├── Week3
    ├── Jupyter
    │   ├── docker-compose.yaml
    │   └── notebooks
    │   │   ├── .ipynb_checkpoints
    │   │       └── PySparkTasksTemplate-checkpoint.ipynb
    │   │   ├── PySparkTasksTemplate.ipynb
    │   │   ├── taxi_cars_data.parquet
    │   │   └── taxi_data.parquet
    ├── Project
    │   ├── PySparkJob.py
    │   └── clickstream.parquet
    ├── help.txt
    ├── spark-practice
    │   ├── PySpark.ipynb
    │   ├── PySparkTitanikJob.ipynb
    │   └── train.csv
    └── spark-tasks
    │   ├── PySparkTasksTemplate.ipynb
    │   ├── taxi_cars_data.parquet
    │   └── taxi_data.parquet
├── Week4
    ├── Airflow
    │   ├── container-data
    │   │   └── airflow
    │   │   │   └── dags
    │   │   │       ├── calculate_dag.py
    │   │   │       ├── calculate_parallel_dag.py
    │   │   │       ├── dummy_dag.py
    │   │   │       └── hello_dag.py
    │   └── docker-compose.yaml
    └── help.txt
├── Week5
    ├── SparkML
    │   ├── Project
    │   │   ├── PySparkMLFit.py
    │   │   ├── PySparkMLPredict.py
    │   │   ├── test.parquet
    │   │   └── train.parquet
    │   ├── spark-practice
    │   │   ├── TitanikSparkML.ipynb
    │   │   ├── cat_dog
    │   │   │   ├── PySparkMLDL.ipynb
    │   │   │   ├── cat_dog.zip
    │   │   │   ├── scala-logging_2.11-3.9.2.jar
    │   │   │   └── tensorframes-0.6.0-s_2.11.jar
    │   │   └── train.csv
    │   └── spark-tasks
    │   │   ├── SparkMLTemplate.ipynb
    │   │   ├── iris.parquet
    │   │   ├── linear_regression.parquet
    │   │   └── wine.parquet
    └── help.txt
├── Week6
    ├── Superset
    │   ├── .env
    │   ├── config
    │   │   └── superset_config.py
    │   └── docker-compose.yaml
    └── help.txt
└── workshops
    ├── 1. DB_Hadoop
        ├── CAP-Theorem.png
        ├── docker-hadoop
        │   ├── docker-compose.yml
        │   ├── hadoop.env
        │   ├── init4win.bat
        │   └── tmp
        │   │   ├── data
        │   │       ├── checkdata.txt
        │   │       ├── checkdata2.txt
        │   │       ├── checkdata3.txt
        │   │       ├── checkdata4.txt
        │   │       └── checkdata5.txt
        │   │   ├── init
        │   │       └── init.sh
        │   │   └── input
        │   │       └── input.txt
        └── hadoop-with-hive
        │   ├── README.md
        │   ├── data
        │       ├── create.sql
        │       ├── init.sh
        │       ├── users_20210501.csv
        │       └── users_20210502.csv
        │   ├── docker-compose.yml
        │   └── hadoop.env
    ├── 2. Spark
        ├── PySparkShow.ipynb
        ├── Spark
        │   ├── PySparkJob.py
        │   ├── docker-compose.yml
        │   └── help.txt
        ├── Streaming
        │   ├── WordStream
        │   │   ├── WordStream.py
        │   │   └── commands.txt
        │   └── docker-compose.yml
        └── taxi_data.parquet
    ├── 3. Airflow
        ├── container-data
        │   └── airflow
        │   │   └── dags
        │   │       ├── calculate_dag.py
        │   │       ├── calculate_parallel_dag.py
        │   │       ├── dummy_dag.py
        │   │       ├── hello_dag.py
        │   │       └── test_dag.py
        └── docker-compose.yaml
    └── 4. Spark ML
        ├── TitanikSparkML.ipynb
        ├── test.csv
        └── train.csv


/.gitattributes:
--------------------------------------------------------------------------------
1 | *.sql linguist-detectable=false


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | # Compiled class file
 2 | *.class
 3 | 
 4 | # Log file
 5 | *.log
 6 | 
 7 | # BlueJ files
 8 | *.ctxt
 9 | 
10 | # Mobile Tools for Java (J2ME)
11 | .mtj.tmp/
12 | 
13 | # Package Files #
14 | *.jar
15 | *.war
16 | *.nar
17 | *.ear
18 | *.zip
19 | *.tar.gz
20 | *.rar
21 | 
22 | # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
23 | hs_err_pid*
24 | .idea
25 | !/Week2/docker-hadoop/tmp/job/mr-wordcount.jar
26 | !/Week5/SparkML/spark-practice/cat_dog/scala-logging_2.11-3.9.2.jar
27 | !/Week5/SparkML/spark-practice/cat_dog/tensorframes-0.6.0-s_2.11.jar
28 | !/Week5/SparkML/spark-practice/cat_dog/cat_dog.zip
29 | /Week1/Postgres/container-data/postgres/data/
30 | /venv/
31 | .cache/
32 | .ipynb_checkpoints/
33 | .ipython/
34 | .jupyter/
35 | .local/
36 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 |                                  Apache License
  2 |                            Version 2.0, January 2004
  3 |                         http://www.apache.org/licenses/
  4 | 
  5 |    TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
  6 | 
  7 |    1. Definitions.
  8 | 
  9 |       "License" shall mean the terms and conditions for use, reproduction,
 10 |       and distribution as defined by Sections 1 through 9 of this document.
 11 | 
 12 |       "Licensor" shall mean the copyright owner or entity authorized by
 13 |       the copyright owner that is granting the License.
 14 | 
 15 |       "Legal Entity" shall mean the union of the acting entity and all
 16 |       other entities that control, are controlled by, or are under common
 17 |       control with that entity. For the purposes of this definition,
 18 |       "control" means (i) the power, direct or indirect, to cause the
 19 |       direction or management of such entity, whether by contract or
 20 |       otherwise, or (ii) ownership of fifty percent (50%) or more of the
 21 |       outstanding shares, or (iii) beneficial ownership of such entity.
 22 | 
 23 |       "You" (or "Your") shall mean an individual or Legal Entity
 24 |       exercising permissions granted by this License.
 25 | 
 26 |       "Source" form shall mean the preferred form for making modifications,
 27 |       including but not limited to software source code, documentation
 28 |       source, and configuration files.
 29 | 
 30 |       "Object" form shall mean any form resulting from mechanical
 31 |       transformation or translation of a Source form, including but
 32 |       not limited to compiled object code, generated documentation,
 33 |       and conversions to other media types.
 34 | 
 35 |       "Work" shall mean the work of authorship, whether in Source or
 36 |       Object form, made available under the License, as indicated by a
 37 |       copyright notice that is included in or attached to the work
 38 |       (an example is provided in the Appendix below).
 39 | 
 40 |       "Derivative Works" shall mean any work, whether in Source or Object
 41 |       form, that is based on (or derived from) the Work and for which the
 42 |       editorial revisions, annotations, elaborations, or other modifications
 43 |       represent, as a whole, an original work of authorship. For the purposes
 44 |       of this License, Derivative Works shall not include works that remain
 45 |       separable from, or merely link (or bind by name) to the interfaces of,
 46 |       the Work and Derivative Works thereof.
 47 | 
 48 |       "Contribution" shall mean any work of authorship, including
 49 |       the original version of the Work and any modifications or additions
 50 |       to that Work or Derivative Works thereof, that is intentionally
 51 |       submitted to Licensor for inclusion in the Work by the copyright owner
 52 |       or by an individual or Legal Entity authorized to submit on behalf of
 53 |       the copyright owner. For the purposes of this definition, "submitted"
 54 |       means any form of electronic, verbal, or written communication sent
 55 |       to the Licensor or its representatives, including but not limited to
 56 |       communication on electronic mailing lists, source code control systems,
 57 |       and issue tracking systems that are managed by, or on behalf of, the
 58 |       Licensor for the purpose of discussing and improving the Work, but
 59 |       excluding communication that is conspicuously marked or otherwise
 60 |       designated in writing by the copyright owner as "Not a Contribution."
 61 | 
 62 |       "Contributor" shall mean Licensor and any individual or Legal Entity
 63 |       on behalf of whom a Contribution has been received by Licensor and
 64 |       subsequently incorporated within the Work.
 65 | 
 66 |    2. Grant of Copyright License. Subject to the terms and conditions of
 67 |       this License, each Contributor hereby grants to You a perpetual,
 68 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 69 |       copyright license to reproduce, prepare Derivative Works of,
 70 |       publicly display, publicly perform, sublicense, and distribute the
 71 |       Work and such Derivative Works in Source or Object form.
 72 | 
 73 |    3. Grant of Patent License. Subject to the terms and conditions of
 74 |       this License, each Contributor hereby grants to You a perpetual,
 75 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 76 |       (except as stated in this section) patent license to make, have made,
 77 |       use, offer to sell, sell, import, and otherwise transfer the Work,
 78 |       where such license applies only to those patent claims licensable
 79 |       by such Contributor that are necessarily infringed by their
 80 |       Contribution(s) alone or by combination of their Contribution(s)
 81 |       with the Work to which such Contribution(s) was submitted. If You
 82 |       institute patent litigation against any entity (including a
 83 |       cross-claim or counterclaim in a lawsuit) alleging that the Work
 84 |       or a Contribution incorporated within the Work constitutes direct
 85 |       or contributory patent infringement, then any patent licenses
 86 |       granted to You under this License for that Work shall terminate
 87 |       as of the date such litigation is filed.
 88 | 
 89 |    4. Redistribution. You may reproduce and distribute copies of the
 90 |       Work or Derivative Works thereof in any medium, with or without
 91 |       modifications, and in Source or Object form, provided that You
 92 |       meet the following conditions:
 93 | 
 94 |       (a) You must give any other recipients of the Work or
 95 |           Derivative Works a copy of this License; and
 96 | 
 97 |       (b) You must cause any modified files to carry prominent notices
 98 |           stating that You changed the files; and
 99 | 
100 |       (c) You must retain, in the Source form of any Derivative Works
101 |           that You distribute, all copyright, patent, trademark, and
102 |           attribution notices from the Source form of the Work,
103 |           excluding those notices that do not pertain to any part of
104 |           the Derivative Works; and
105 | 
106 |       (d) If the Work includes a "NOTICE" text file as part of its
107 |           distribution, then any Derivative Works that You distribute must
108 |           include a readable copy of the attribution notices contained
109 |           within such NOTICE file, excluding those notices that do not
110 |           pertain to any part of the Derivative Works, in at least one
111 |           of the following places: within a NOTICE text file distributed
112 |           as part of the Derivative Works; within the Source form or
113 |           documentation, if provided along with the Derivative Works; or,
114 |           within a display generated by the Derivative Works, if and
115 |           wherever such third-party notices normally appear. The contents
116 |           of the NOTICE file are for informational purposes only and
117 |           do not modify the License. You may add Your own attribution
118 |           notices within Derivative Works that You distribute, alongside
119 |           or as an addendum to the NOTICE text from the Work, provided
120 |           that such additional attribution notices cannot be construed
121 |           as modifying the License.
122 | 
123 |       You may add Your own copyright statement to Your modifications and
124 |       may provide additional or different license terms and conditions
125 |       for use, reproduction, or distribution of Your modifications, or
126 |       for any such Derivative Works as a whole, provided Your use,
127 |       reproduction, and distribution of the Work otherwise complies with
128 |       the conditions stated in this License.
129 | 
130 |    5. Submission of Contributions. Unless You explicitly state otherwise,
131 |       any Contribution intentionally submitted for inclusion in the Work
132 |       by You to the Licensor shall be under the terms and conditions of
133 |       this License, without any additional terms or conditions.
134 |       Notwithstanding the above, nothing herein shall supersede or modify
135 |       the terms of any separate license agreement you may have executed
136 |       with Licensor regarding such Contributions.
137 | 
138 |    6. Trademarks. This License does not grant permission to use the trade
139 |       names, trademarks, service marks, or product names of the Licensor,
140 |       except as required for reasonable and customary use in describing the
141 |       origin of the Work and reproducing the content of the NOTICE file.
142 | 
143 |    7. Disclaimer of Warranty. Unless required by applicable law or
144 |       agreed to in writing, Licensor provides the Work (and each
145 |       Contributor provides its Contributions) on an "AS IS" BASIS,
146 |       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 |       implied, including, without limitation, any warranties or conditions
148 |       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 |       PARTICULAR PURPOSE. You are solely responsible for determining the
150 |       appropriateness of using or redistributing the Work and assume any
151 |       risks associated with Your exercise of permissions under this License.
152 | 
153 |    8. Limitation of Liability. In no event and under no legal theory,
154 |       whether in tort (including negligence), contract, or otherwise,
155 |       unless required by applicable law (such as deliberate and grossly
156 |       negligent acts) or agreed to in writing, shall any Contributor be
157 |       liable to You for damages, including any direct, indirect, special,
158 |       incidental, or consequential damages of any character arising as a
159 |       result of this License or out of the use or inability to use the
160 |       Work (including but not limited to damages for loss of goodwill,
161 |       work stoppage, computer failure or malfunction, or any and all
162 |       other commercial damages or losses), even if such Contributor
163 |       has been advised of the possibility of such damages.
164 | 
165 |    9. Accepting Warranty or Additional Liability. While redistributing
166 |       the Work or Derivative Works thereof, You may choose to offer,
167 |       and charge a fee for, acceptance of support, warranty, indemnity,
168 |       or other liability obligations and/or rights consistent with this
169 |       License. However, in accepting such obligations, You may act only
170 |       on Your own behalf and on Your sole responsibility, not on behalf
171 |       of any other Contributor, and only if You agree to indemnify,
172 |       defend, and hold each Contributor harmless for any liability
173 |       incurred by, or claims asserted against, such Contributor by reason
174 |       of your accepting any such warranty or additional liability.
175 | 
176 |    END OF TERMS AND CONDITIONS
177 | 
178 |    APPENDIX: How to apply the Apache License to your work.
179 | 
180 |       To apply the Apache License to your work, attach the following
181 |       boilerplate notice, with the fields enclosed by brackets "[]"
182 |       replaced with your own identifying information. (Don't include
183 |       the brackets!)  The text should be enclosed in the appropriate
184 |       comment syntax for the file format. We also recommend that a
185 |       file or class name and description of purpose be included on the
186 |       same "printed page" as the copyright notice for easier
187 |       identification within third-party archives.
188 | 
189 |    Copyright [yyyy] [name of copyright owner]
190 | 
191 |    Licensed under the Apache License, Version 2.0 (the "License");
192 |    you may not use this file except in compliance with the License.
193 |    You may obtain a copy of the License at
194 | 
195 |        http://www.apache.org/licenses/LICENSE-2.0
196 | 
197 |    Unless required by applicable law or agreed to in writing, software
198 |    distributed under the License is distributed on an "AS IS" BASIS,
199 |    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 |    See the License for the specific language governing permissions and
201 |    limitations under the License.
202 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Big Data for Data Science
 2 | ## [Stepic Academy Course [RU]](https://academy.stepik.org/big-data)
 3 | Репозиторий содержит docker конфигурации, шаблоны и данные необходимые для выполнения практических задач курса.
 4 | * Week1 - SQL
 5 | * Week2 - Hadoop
 6 | * Week3 - Spark
 7 | * Week4 - Workflow/Airflow
 8 | * Week5 - SparkML
 9 | * Week6 - BI/Superset
10 | * Workshops


--------------------------------------------------------------------------------
/Week1/ClickHouse/docker-compose.yml:
--------------------------------------------------------------------------------
 1 | version: "3"
 2 | services:
 3 |   server:
 4 |     image: yandex/clickhouse-server:19.13
 5 |     restart: always
 6 |     ports:
 7 |       - "8123:8123"
 8 |       - "9000:9000"
 9 |       - "9009:9009"
10 |     volumes:
11 |       - ./container-data/clickhouse/data:/var/lib/clickhouse
12 |     ulimits:
13 |       nproc: 65535
14 |       nofile:
15 |         soft: 262144
16 |         hard: 262144
17 |   client:
18 |     image: yandex/clickhouse-client:19.13
19 |     command: ['--host', 'server']
20 | 


--------------------------------------------------------------------------------
/Week1/Postgres/docker-compose.yaml:
--------------------------------------------------------------------------------
 1 | version: '3'
 2 | services:
 3 |   postgres:
 4 |     image: postgres:10
 5 |     restart: always
 6 |     ports:
 7 |     - 5555:5432
 8 |     environment:
 9 |       POSTGRES_PASSWORD: admin
10 |       POSTGRES_DB: course
11 |       POSTGRES_USER: admin
12 |       PGDATA: /tmp
13 |     volumes:
14 |     - ./container-data/postgres/data:/var/lib/postgresql/data
15 |     - ./container-data/postgres/init.sql:/docker-entrypoint-initdb.d/init.sql
16 | 


--------------------------------------------------------------------------------
/Week1/employee.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week1/employee.png


--------------------------------------------------------------------------------
/Week1/help.txt:
--------------------------------------------------------------------------------
 1 | Запуск PostgreSQL (Выполнять из папки Week1/Postgres)
 2 | 1) Запуск контейнеров
 3 |     docker-compose up -d
 4 | 2) Проверка запущенных контейнеров
 5 |     docker ps
 6 | 3) Соединение к БД
 7 |     host: localhost
 8 |     port: 5555
 9 |     database: course
10 |     login: admin
11 |     password: admin
12 | 4) Выполнение SQL
13 |     ...
14 | 5) Остановка контейнеров
15 |     docker-compose down
16 | 
17 | Запуск ClickHouse (Выполнять из папки Week1/ClickHouse)
18 | 1) Запуск контейнеров
19 |     docker-compose up -d
20 | 2) Проверка запущенных контейнеров
21 |     docker ps
22 | 3) Соединение к БД
23 |     host: localhost
24 |     port: 8123
25 |     database:
26 |     login:
27 |     password:
28 | 4) Выполнение SQL


--------------------------------------------------------------------------------
/Week1/practice.sql:
--------------------------------------------------------------------------------
 1 | -- 1. Простые запросы
 2 | select * from employee;
 3 | select id, name, surname from employee;
 4 | select id, name, surname from employee limit 10;
 5 | select id, concat(name, ' ', surname) as fio from employee;
 6 | 
 7 | -- 2. Применение аггрегирующих функций
 8 | select count(*) from employee;
 9 | select count(*), max(salary), min(salary), avg(salary) from employee;
10 | 
11 | -- 3. Применение ограничивающих условий
12 | select count(*) from employee
13 | where salary > 5000;
14 | 
15 | select count(*) from employee
16 | where salary > 5000 and salary < 8000;
17 | 
18 | select count(*) from employee
19 | where salary >= 8000 or salary <= 5000;
20 | 
21 | select count(*) from employee
22 | where name = 'Tom';
23 | 
24 | select count(*) from employee
25 | where name in ('Tom', 'Mark', 'Kate');
26 | 
27 | select count(*) from employee
28 | where name like 'A%'; -- % - любое число символов
29 | 
30 | -- Число сотрудников с именем начинающимся на А и из 4 букв
31 | select count(*) from employee
32 | where name like 'A___'; -- _ - один любой символ
33 | 
34 | -- Число сотрудников с именем из 4 букв
35 | select count(*) from employee
36 | where length(name) = 4;
37 | 
38 | -- 4. Группировка и упорядочивание данных
39 | select name, count(name) from employee
40 | where length(name) > 3
41 | group by name;
42 | 
43 | select name, count(name) as count from employee
44 | where length(name) > 3
45 | group by name
46 | order by count desc;
47 | 
48 | select name, count(name) as count from employee
49 | where length(name) > 3
50 | group by name
51 | having count(name) >= 150
52 | order by count desc;
53 | 
54 | -- группировки и упорядочивания отлично подходят при решений для нахождения самых популярных значений
55 | select name, count(name) as count from employee
56 | group by name
57 | order by count desc
58 | limit 3;
59 | 
60 | 
61 | -- 5. Join
62 | select c.name, o.country from office o
63 | join company c on o.company_id = c.id;
64 | 
65 | select distinct c.name, o.country from office o
66 | join company c on o.company_id = c.id
67 | order by name;
68 | 
69 | -- 6. Вложенные запросы
70 | -- Список сотрудников с зарплатой выше средней
71 | select name, surname from employee
72 | where salary > (select avg(salary) from employee);
73 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/docker-compose.yml:
--------------------------------------------------------------------------------
 1 | version: "3"
 2 | 
 3 | services:
 4 |   namenode:
 5 |     image: bde2020/hadoop-namenode:2.0.0-hadoop3.2.1-java8
 6 |     container_name: namenode
 7 |     restart: always
 8 |     ports:
 9 |       - 9870:9870
10 |       - 9000:9000
11 |     volumes:
12 |       - hadoop_namenode:/hadoop/dfs/name
13 |       - ./tmp/data:/course/data
14 |       - ./tmp/input:/course/input
15 |       - ./tmp/job:/job
16 |       - ./tmp/init:/init
17 |     #command: sh /init/init.sh
18 |     environment:
19 |       - CLUSTER_NAME=test
20 |     env_file:
21 |       - ./hadoop.env
22 | 
23 |   datanode:
24 |     image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
25 |     container_name: datanode
26 |     restart: always
27 |     volumes:
28 |       - hadoop_datanode:/hadoop/dfs/data
29 |     environment:
30 |       SERVICE_PRECONDITION: "namenode:9870"
31 |     env_file:
32 |       - ./hadoop.env
33 | 
34 |   resourcemanager:
35 |     image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.2.1-java8
36 |     container_name: resourcemanager
37 |     restart: always
38 |     ports:
39 |       - 8088:8088
40 |     environment:
41 |       SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864"
42 |     env_file:
43 |       - ./hadoop.env
44 | 
45 |   nodemanager1:
46 |     image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.2.1-java8
47 |     container_name: nodemanager
48 |     restart: always
49 |     environment:
50 |       SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
51 |     env_file:
52 |       - ./hadoop.env
53 | 
54 |   historyserver:
55 |     image: bde2020/hadoop-historyserver:2.0.0-hadoop3.2.1-java8
56 |     container_name: historyserver
57 |     restart: always
58 |     environment:
59 |       SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
60 |     volumes:
61 |       - hadoop_historyserver:/hadoop/yarn/timeline
62 |     env_file:
63 |       - ./hadoop.env
64 | 
65 | volumes:
66 |   hadoop_namenode:
67 |   hadoop_datanode:
68 |   hadoop_historyserver:
69 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/hadoop.env:
--------------------------------------------------------------------------------
 1 | CORE_CONF_fs_defaultFS=hdfs://namenode:9000
 2 | CORE_CONF_hadoop_http_staticuser_user=root
 3 | CORE_CONF_hadoop_proxyuser_hue_hosts=*
 4 | CORE_CONF_hadoop_proxyuser_hue_groups=*
 5 | CORE_CONF_io_compression_codecs=org.apache.hadoop.io.compress.SnappyCodec
 6 | 
 7 | HDFS_CONF_dfs_webhdfs_enabled=true
 8 | HDFS_CONF_dfs_permissions_enabled=false
 9 | HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false
10 | 
11 | YARN_CONF_yarn_log___aggregation___enable=true
12 | YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
13 | YARN_CONF_yarn_resourcemanager_recovery_enabled=true
14 | YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
15 | YARN_CONF_yarn_resourcemanager_scheduler_class=org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler
16 | YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___mb=8192
17 | YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___vcores=4
18 | YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
19 | YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
20 | YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
21 | YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
22 | YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
23 | YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031
24 | YARN_CONF_yarn_timeline___service_enabled=true
25 | YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
26 | YARN_CONF_yarn_timeline___service_hostname=historyserver
27 | YARN_CONF_mapreduce_map_output_compress=true
28 | YARN_CONF_mapred_map_output_compress_codec=org.apache.hadoop.io.compress.SnappyCodec
29 | YARN_CONF_yarn_nodemanager_resource_memory___mb=16384
30 | YARN_CONF_yarn_nodemanager_resource_cpu___vcores=8
31 | YARN_CONF_yarn_nodemanager_disk___health___checker_max___disk___utilization___per___disk___percentage=98.5
32 | YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
33 | YARN_CONF_yarn_nodemanager_aux___services=mapreduce_shuffle
34 | 
35 | MAPRED_CONF_mapreduce_framework_name=yarn
36 | MAPRED_CONF_mapred_child_java_opts=-Xmx4096m
37 | MAPRED_CONF_mapreduce_map_memory_mb=4096
38 | MAPRED_CONF_mapreduce_reduce_memory_mb=8192
39 | MAPRED_CONF_mapreduce_map_java_opts=-Xmx3072m
40 | MAPRED_CONF_mapreduce_reduce_java_opts=-Xmx6144m
41 | MAPRED_CONF_yarn_app_mapreduce_am_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
42 | MAPRED_CONF_mapreduce_map_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
43 | MAPRED_CONF_mapreduce_reduce_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/


--------------------------------------------------------------------------------
/Week2/docker-hadoop/init4win7.bat:
--------------------------------------------------------------------------------
1 | @ECHO OFF
2 | docker cp ./tmp/data namenode:/course/data
3 | docker cp ./tmp/input namenode:/course/input
4 | docker cp ./tmp/job namenode:/job
5 | docker cp ./tmp/init namenode:/init
6 | ECHO All data has been copied successfully.


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/data/checkdata.txt:
--------------------------------------------------------------------------------
1 | Big Data = Big Issues
2 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/data/checkdata2.txt:
--------------------------------------------------------------------------------
1 | 0101020201020304038974589381219038190288237520834203482039529874359273648723658743753094589023842093742983759843658734643808203482935839485739464389572037409238420938023975394857394653487230423094820934820385739486538746583457289470239482093842093850394739846794836598347528947092384209384209375938457394865834752837402398402938409235830945739845769384653984752093480298405938450934759836798347534759304597
2 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/data/checkdata3.txt:
--------------------------------------------------------------------------------
1 | 0101020201020304038974589381219038190288237520834203482039529874359273648723658743753094589023842093742983759843658734643808203482935839485739464389572037409238420938023975394857394653487230423094820934820385739486538746583457289470239482093842093850394739846794836598347528947092384209384209375938457394865834752837402398402938409235830945739845769384653984752093480298405938450934759836798347534759304597
2 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/data/checkdata4.txt:
--------------------------------------------------------------------------------
1 | Data4
2 | 
3 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/data/checkdata5.txt:
--------------------------------------------------------------------------------
1 | Data5
2 | 
3 | 


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/init/init.sh:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env bash
2 | hdfs dfs -mkdir /data
3 | hdfs dfs -mkdir /input
4 | hdfs dfs -put /course/data/* /data
5 | hdfs dfs -put /course/input/* /input
6 | echo "Initialization complete"


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/input/input2.txt:
--------------------------------------------------------------------------------
1 | Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Big Data Big Data Big Data Big Data Big Data Big Data Big Data Stepik Data Science Data Science Data Science Data Science Data Science Data Science Data Science Data Science Stepik Data Science Data Science Data Science Data Science Data Science Data Science


--------------------------------------------------------------------------------
/Week2/docker-hadoop/tmp/job/mr-wordcount.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week2/docker-hadoop/tmp/job/mr-wordcount.jar


--------------------------------------------------------------------------------
/Week2/help.txt:
--------------------------------------------------------------------------------
 1 | Выполнять из папки Week2/docker-hadoop
 2 | 1) Запуск контейнеров
 3 |     docker-compose up -d
 4 | 2) Проверка запущенных контейнеров
 5 |     docker ps
 6 | 3) Hadoop UI
 7 |     http://localhost:9870
 8 | 4) Подключение к NameNode
 9 |     docker exec -it namenode bash
10 | 5) Выполнение команд в HDFS
11 |     ...
12 | 6) Запуск MapReduce (Java)
13 |     hadoop jar /job/mr-wordcount.jar org.apache.hadoop.examples.WordCount /input /output
14 | 7) Выход из контейнера
15 |     exit
16 | 8) Остановка контейнеров
17 |     docker-compose down
18 | ВАЖНО!
19 | 9) После остановки контейнеров выполните команду:
20 |     docker system prune —-volumes
21 |    И выбирете Yes(Y) для удаления метаинформации кластера.


--------------------------------------------------------------------------------
/Week3/Jupyter/docker-compose.yaml:
--------------------------------------------------------------------------------
 1 | version: '3'
 2 | services:
 3 |   jupyter-pyspark:
 4 |     image: jupyter/pyspark-notebook:4d9c9bd9ced0
 5 |     command: start.sh jupyter notebook --NotebookApp.token=''
 6 |     restart: always
 7 |     ports:
 8 |     - 8888:8888
 9 |     - 4040:4040
10 |     volumes:
11 |     - ./notebooks:/home/jovyan


--------------------------------------------------------------------------------
/Week3/Jupyter/notebooks/.ipynb_checkpoints/PySparkTasksTemplate-checkpoint.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#   @@@@@@@     @      @    @  @   #\n",
 10 |     "#   @  @  @    @ @      @  @       #\n",
 11 |     "#      @  @   @   @      @@    @   #\n",
 12 |     "#      @     @@@@@@@    @  @   @   #\n",
 13 |     "#      @    @       @  @    @  @   #"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "markdown",
 18 |    "metadata": {},
 19 |    "source": [
 20 |     "Привет, в этой практике мы с вами применим наши знания по PySpark и постараемся изучить что-то новое в процессе выполнения.\n",
 21 |     "<br>В занятии используется датасет собранный на основе данных <a href=\"https://www.kaggle.com/chicago/chicago-taxi-rides-2016\">Chicago Taxi Rides 2016</a>\n",
 22 |     "<br>Полная <a href=\"https://spark.apache.org/docs/latest/api/python/index.html\">документация PySpark</a>.\n",
 23 |     "<br>Схема данны:\n",
 24 |     "<br>|-- taxi_id = идентификатор таксиста\n",
 25 |     "<br>|-- trip_start_timestamp = время начала поездки\n",
 26 |     "<br>|-- trip_end_timestamp = время окончания поездки\n",
 27 |     "<br>|-- trip_seconds = время длительности поездки в секундах\n",
 28 |     "<br>|-- trip_miles = мили проиденные во время поездки\n",
 29 |     "<br>|-- fare = транспортные расходы\n",
 30 |     "<br>|-- tips = назначенные чаевые\n",
 31 |     "<br>|-- trip_total = общая стоимость поездки (Итоговая с учетом чаевых и расходов)\n",
 32 |     "<br>|-- payment_type = тип оплаты"
 33 |    ]
 34 |   },
 35 |   {
 36 |    "cell_type": "code",
 37 |    "execution_count": null,
 38 |    "metadata": {},
 39 |    "outputs": [],
 40 |    "source": [
 41 |     "from pyspark.sql import SparkSession\n",
 42 |     "from pyspark.sql.functions import col"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": null,
 48 |    "metadata": {},
 49 |    "outputs": [],
 50 |    "source": [
 51 |     "spark = SparkSession.builder.appName('PySparkTasks').getOrCreate()"
 52 |    ]
 53 |   },
 54 |   {
 55 |    "cell_type": "code",
 56 |    "execution_count": null,
 57 |    "metadata": {},
 58 |    "outputs": [],
 59 |    "source": [
 60 |     "spark.conf.set(\"spark.sql.session.timeZone\", \"GMT+3\")"
 61 |    ]
 62 |   },
 63 |   {
 64 |    "cell_type": "code",
 65 |    "execution_count": null,
 66 |    "metadata": {},
 67 |    "outputs": [],
 68 |    "source": [
 69 |     "spark"
 70 |    ]
 71 |   },
 72 |   {
 73 |    "cell_type": "markdown",
 74 |    "metadata": {},
 75 |    "source": [
 76 |     "Скачайте <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week3/spark-tasks/taxi_data.parquet\">taxi_data.parquet</a> и загрузите используя <a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark.sql.DataFrame\">SparkAPI</a>"
 77 |    ]
 78 |   },
 79 |   {
 80 |    "cell_type": "code",
 81 |    "execution_count": null,
 82 |    "metadata": {},
 83 |    "outputs": [],
 84 |    "source": [
 85 |     "df = #Ваш код загрузки"
 86 |    ]
 87 |   },
 88 |   {
 89 |    "cell_type": "markdown",
 90 |    "metadata": {},
 91 |    "source": [
 92 |     "№1 Посчитайте количество загруженных строк."
 93 |    ]
 94 |   },
 95 |   {
 96 |    "cell_type": "code",
 97 |    "execution_count": null,
 98 |    "metadata": {},
 99 |    "outputs": [],
100 |    "source": [
101 |     "# Число строк"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": null,
107 |    "metadata": {},
108 |    "outputs": [],
109 |    "source": [
110 |     "df.show()"
111 |    ]
112 |   },
113 |   {
114 |    "cell_type": "markdown",
115 |    "metadata": {},
116 |    "source": [
117 |     "Посмотрим схему данных:"
118 |    ]
119 |   },
120 |   {
121 |    "cell_type": "code",
122 |    "execution_count": null,
123 |    "metadata": {},
124 |    "outputs": [],
125 |    "source": [
126 |     "df.printSchema()"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "markdown",
131 |    "metadata": {},
132 |    "source": [
133 |     "№2 Чему равна корреляция и ковариация между длиной маршрута и ценой за поездку? Ответ округлите до 5 знаков после запятой.\n",
134 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.corr.html?highlight=corr#pyspark-sql-dataframe-corr\">corr</a> & <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.cov.html?highlight=cov#pyspark-sql-dataframe-cov\">cov</a>"
135 |    ]
136 |   },
137 |   {
138 |    "cell_type": "code",
139 |    "execution_count": null,
140 |    "metadata": {},
141 |    "outputs": [],
142 |    "source": [
143 |     "# Ваш код"
144 |    ]
145 |   },
146 |   {
147 |    "cell_type": "markdown",
148 |    "metadata": {},
149 |    "source": [
150 |     "№3 Найдите количество, среднее, cреднеквадратическое отклонение, минимум и максимум для длины маршрута и цены за поездку? Ответ округлите до 1 знака после запятой. Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.describe.html?highlight=describe#pyspark-sql-dataframe-describe\">describe</a>"
151 |    ]
152 |   },
153 |   {
154 |    "cell_type": "code",
155 |    "execution_count": null,
156 |    "metadata": {},
157 |    "outputs": [],
158 |    "source": [
159 |     "# Ваш код"
160 |    ]
161 |   },
162 |   {
163 |    "cell_type": "markdown",
164 |    "metadata": {},
165 |    "source": [
166 |     "№4 Найдите самый НЕпопулярный вид оплаты.\n",
167 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.groupBy.html?highlight=groupby#pyspark-sql-dataframe-groupby\">groupBy</a> <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.orderBy.html?highlight=orderby#pyspark-sql-dataframe-orderby\">orderBy</a>"
168 |    ]
169 |   },
170 |   {
171 |    "cell_type": "code",
172 |    "execution_count": null,
173 |    "metadata": {},
174 |    "outputs": [],
175 |    "source": [
176 |     "# Ваш код"
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "markdown",
181 |    "metadata": {},
182 |    "source": [
183 |     "№5 Найдите идентификатор таксиста выполнившего наибольшее число заказов."
184 |    ]
185 |   },
186 |   {
187 |    "cell_type": "code",
188 |    "execution_count": null,
189 |    "metadata": {},
190 |    "outputs": [],
191 |    "source": [
192 |     "# Ваш код"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "markdown",
197 |    "metadata": {},
198 |    "source": [
199 |     "№6 Чему равна средняя цена среди поездок, оплаченных наличными? Ответ округлите до 5 знака.\n",
200 |     "<br> Подробней <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.where.html?highlight=where#pyspark-sql-dataframe-where\">where</a>"
201 |    ]
202 |   },
203 |   {
204 |    "cell_type": "code",
205 |    "execution_count": null,
206 |    "metadata": {},
207 |    "outputs": [],
208 |    "source": [
209 |     "# Ваш код"
210 |    ]
211 |   },
212 |   {
213 |    "cell_type": "markdown",
214 |    "metadata": {},
215 |    "source": [
216 |     "№7 Сколько таксистов проехало больше 1000 миль за все время выполнения заказов?"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": null,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "# Ваш код"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "markdown",
230 |    "metadata": {},
231 |    "source": [
232 |     "№8 Сколько миль проехал пассажир в самой долгой поездке? (Ответ округлите до целого)"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": null,
238 |    "metadata": {},
239 |    "outputs": [],
240 |    "source": [
241 |     "# Ваш код"
242 |    ]
243 |   },
244 |   {
245 |    "cell_type": "markdown",
246 |    "metadata": {},
247 |    "source": [
248 |     "№9 Каков средний заработок всех таксистов? Ответ округлите до 5-ого знака.\n",
249 |     "<br>Отсеките неизвестные машины (не определенный taxi_id)."
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": null,
255 |    "metadata": {},
256 |    "outputs": [],
257 |    "source": [
258 |     "# Ваш код"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "markdown",
263 |    "metadata": {},
264 |    "source": [
265 |     "№10 Сколько поездок начиналось в самый загруженный час?\n",
266 |     "<br>Используйте функцию <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.hour.html?highlight=hour#pyspark-sql-functions-hour\">hour</a>"
267 |    ]
268 |   },
269 |   {
270 |    "cell_type": "code",
271 |    "execution_count": null,
272 |    "metadata": {},
273 |    "outputs": [],
274 |    "source": [
275 |     "from pyspark.sql.functions import hour"
276 |    ]
277 |   },
278 |   {
279 |    "cell_type": "code",
280 |    "execution_count": null,
281 |    "metadata": {},
282 |    "outputs": [],
283 |    "source": [
284 |     "# Ваш код"
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "markdown",
289 |    "metadata": {},
290 |    "source": [
291 |     "№11 Сколько поездок началось во второй четверти суток?"
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "code",
296 |    "execution_count": null,
297 |    "metadata": {},
298 |    "outputs": [],
299 |    "source": [
300 |     "# Ваш код"
301 |    ]
302 |   },
303 |   {
304 |    "cell_type": "markdown",
305 |    "metadata": {},
306 |    "source": [
307 |     "№12 Найдите топ три даты, в которые было суммарно больше всего чаевых? (Чаевые выдаются после совершения поездки)\n",
308 |     "<br> Ожидаемый формат дат YYYY-MM-DD\n",
309 |     "<br>Вам может понадобится конвертация типов <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.Column.cast.html?highlight=cast#pyspark-sql-column-cast\">cast</a>"
310 |    ]
311 |   },
312 |   {
313 |    "cell_type": "code",
314 |    "execution_count": null,
315 |    "metadata": {},
316 |    "outputs": [],
317 |    "source": [
318 |     "from pyspark.sql.types import DateType"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": null,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "# Ваш код"
328 |    ]
329 |   },
330 |   {
331 |    "cell_type": "markdown",
332 |    "metadata": {},
333 |    "source": [
334 |     "№13 Сколько было заказов в дату с наибольшим спросом?"
335 |    ]
336 |   },
337 |   {
338 |    "cell_type": "code",
339 |    "execution_count": null,
340 |    "metadata": {},
341 |    "outputs": [],
342 |    "source": [
343 |     "# Ваш код"
344 |    ]
345 |   },
346 |   {
347 |    "cell_type": "markdown",
348 |    "metadata": {},
349 |    "source": [
350 |     "Подгрузите данные о марках машин из датасета <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week3/spark-tasks/taxi_cars_data.parquet\">taxi_cars_data.parquet</a>"
351 |    ]
352 |   },
353 |   {
354 |    "cell_type": "code",
355 |    "execution_count": null,
356 |    "metadata": {},
357 |    "outputs": [],
358 |    "source": [
359 |     "df_car = # Ваш код загрузки"
360 |    ]
361 |   },
362 |   {
363 |    "cell_type": "code",
364 |    "execution_count": null,
365 |    "metadata": {},
366 |    "outputs": [],
367 |    "source": [
368 |     "df_car.show()"
369 |    ]
370 |   },
371 |   {
372 |    "cell_type": "markdown",
373 |    "metadata": {},
374 |    "source": [
375 |     "№14 Какая марка машины самая распрастранненая среди таксистов?\n",
376 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.split.html?highlight=split#pyspark-sql-functions-split\">split</a>"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": null,
382 |    "metadata": {},
383 |    "outputs": [],
384 |    "source": [
385 |     "from pyspark.sql.functions import split"
386 |    ]
387 |   },
388 |   {
389 |    "cell_type": "code",
390 |    "execution_count": null,
391 |    "metadata": {},
392 |    "outputs": [],
393 |    "source": [
394 |     "# Ваш код"
395 |    ]
396 |   },
397 |   {
398 |    "cell_type": "markdown",
399 |    "metadata": {},
400 |    "source": [
401 |     "№15 Сколько раз и какая модель машин чаще всего встречается в поездках?\n",
402 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.split.html?highlight=split#pyspark-sql-functions-split\">join</a>"
403 |    ]
404 |   },
405 |   {
406 |    "cell_type": "code",
407 |    "execution_count": null,
408 |    "metadata": {},
409 |    "outputs": [],
410 |    "source": [
411 |     "# Ваш код"
412 |    ]
413 |   },
414 |   {
415 |    "cell_type": "markdown",
416 |    "metadata": {},
417 |    "source": [
418 |     "Почувствуй силу сжатия! сохрани DataFrame в csv и сравни размеры файлов."
419 |    ]
420 |   },
421 |   {
422 |    "cell_type": "code",
423 |    "execution_count": null,
424 |    "metadata": {},
425 |    "outputs": [],
426 |    "source": [
427 |     "# Ваш код с coalesce(1)"
428 |    ]
429 |   },
430 |   {
431 |    "cell_type": "markdown",
432 |    "metadata": {},
433 |    "source": [
434 |     "Теперь загрузите данные из csv и проверьте типы методом printSchema()."
435 |    ]
436 |   },
437 |   {
438 |    "cell_type": "code",
439 |    "execution_count": null,
440 |    "metadata": {},
441 |    "outputs": [],
442 |    "source": [
443 |     "# Ваш код с printSchema() для DataFrame из csv"
444 |    ]
445 |   },
446 |   {
447 |    "cell_type": "markdown",
448 |    "metadata": {},
449 |    "source": [
450 |     "Не забудьте посетить SparkUI и изучить историю ваших задач."
451 |    ]
452 |   },
453 |   {
454 |    "cell_type": "code",
455 |    "execution_count": null,
456 |    "metadata": {},
457 |    "outputs": [],
458 |    "source": [
459 |     "spark"
460 |    ]
461 |   },
462 |   {
463 |    "cell_type": "code",
464 |    "execution_count": null,
465 |    "metadata": {},
466 |    "outputs": [],
467 |    "source": []
468 |   }
469 |  ],
470 |  "metadata": {
471 |   "kernelspec": {
472 |    "display_name": "Python 3",
473 |    "language": "python",
474 |    "name": "python3"
475 |   },
476 |   "language_info": {
477 |    "codemirror_mode": {
478 |     "name": "ipython",
479 |     "version": 3
480 |    },
481 |    "file_extension": ".py",
482 |    "mimetype": "text/x-python",
483 |    "name": "python",
484 |    "nbconvert_exporter": "python",
485 |    "pygments_lexer": "ipython3",
486 |    "version": "3.7.4"
487 |   }
488 |  },
489 |  "nbformat": 4,
490 |  "nbformat_minor": 2
491 | }
492 | 


--------------------------------------------------------------------------------
/Week3/Jupyter/notebooks/PySparkTasksTemplate.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#   @@@@@@@     @      @    @  @   #\n",
 10 |     "#   @  @  @    @ @      @  @       #\n",
 11 |     "#      @  @   @   @      @@    @   #\n",
 12 |     "#      @     @@@@@@@    @  @   @   #\n",
 13 |     "#      @    @       @  @    @  @   #"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "markdown",
 18 |    "metadata": {},
 19 |    "source": [
 20 |     "Привет, в этой практике мы с вами применим наши знания по PySpark и постараемся изучить что-то новое в процессе выполнения.\n",
 21 |     "<br>В занятии используется датасет собранный на основе данных <a href=\"https://www.kaggle.com/chicago/chicago-taxi-rides-2016\">Chicago Taxi Rides 2016</a>\n",
 22 |     "<br>Полная <a href=\"https://spark.apache.org/docs/latest/api/python/index.html\">документация PySpark</a>.\n",
 23 |     "<br>Схема данны:\n",
 24 |     "<br>|-- taxi_id = идентификатор таксиста\n",
 25 |     "<br>|-- trip_start_timestamp = время начала поездки\n",
 26 |     "<br>|-- trip_end_timestamp = время окончания поездки\n",
 27 |     "<br>|-- trip_seconds = время длительности поездки в секундах\n",
 28 |     "<br>|-- trip_miles = мили проиденные во время поездки\n",
 29 |     "<br>|-- fare = транспортные расходы\n",
 30 |     "<br>|-- tips = назначенные чаевые\n",
 31 |     "<br>|-- trip_total = общая стоимость поездки (Итоговая с учетом чаевых и расходов)\n",
 32 |     "<br>|-- payment_type = тип оплаты"
 33 |    ]
 34 |   },
 35 |   {
 36 |    "cell_type": "code",
 37 |    "execution_count": null,
 38 |    "metadata": {},
 39 |    "outputs": [],
 40 |    "source": [
 41 |     "from pyspark.sql import SparkSession\n",
 42 |     "from pyspark.sql.functions import col"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": null,
 48 |    "metadata": {},
 49 |    "outputs": [],
 50 |    "source": [
 51 |     "spark = SparkSession.builder.appName('PySparkTasks').getOrCreate()"
 52 |    ]
 53 |   },
 54 |   {
 55 |    "cell_type": "code",
 56 |    "execution_count": null,
 57 |    "metadata": {},
 58 |    "outputs": [],
 59 |    "source": [
 60 |     "spark.conf.set(\"spark.sql.session.timeZone\", \"GMT+3\")"
 61 |    ]
 62 |   },
 63 |   {
 64 |    "cell_type": "code",
 65 |    "execution_count": null,
 66 |    "metadata": {},
 67 |    "outputs": [],
 68 |    "source": [
 69 |     "spark"
 70 |    ]
 71 |   },
 72 |   {
 73 |    "cell_type": "markdown",
 74 |    "metadata": {},
 75 |    "source": [
 76 |     "Скачайте <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week3/spark-tasks/taxi_data.parquet\">taxi_data.parquet</a> и загрузите используя <a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark.sql.DataFrame\">SparkAPI</a>"
 77 |    ]
 78 |   },
 79 |   {
 80 |    "cell_type": "code",
 81 |    "execution_count": null,
 82 |    "metadata": {},
 83 |    "outputs": [],
 84 |    "source": [
 85 |     "df = #Ваш код загрузки"
 86 |    ]
 87 |   },
 88 |   {
 89 |    "cell_type": "markdown",
 90 |    "metadata": {},
 91 |    "source": [
 92 |     "№1 Посчитайте количество загруженных строк."
 93 |    ]
 94 |   },
 95 |   {
 96 |    "cell_type": "code",
 97 |    "execution_count": null,
 98 |    "metadata": {},
 99 |    "outputs": [],
100 |    "source": [
101 |     "# Число строк"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": null,
107 |    "metadata": {},
108 |    "outputs": [],
109 |    "source": [
110 |     "df.show()"
111 |    ]
112 |   },
113 |   {
114 |    "cell_type": "markdown",
115 |    "metadata": {},
116 |    "source": [
117 |     "Посмотрим схему данных:"
118 |    ]
119 |   },
120 |   {
121 |    "cell_type": "code",
122 |    "execution_count": null,
123 |    "metadata": {},
124 |    "outputs": [],
125 |    "source": [
126 |     "df.printSchema()"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "markdown",
131 |    "metadata": {},
132 |    "source": [
133 |     "№2 Чему равна корреляция и ковариация между длиной маршрута и ценой за поездку? Ответ округлите до 5 знаков после запятой.\n",
134 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.corr.html?highlight=corr#pyspark-sql-dataframe-corr\">corr</a> & <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.cov.html?highlight=cov#pyspark-sql-dataframe-cov\">cov</a>"
135 |    ]
136 |   },
137 |   {
138 |    "cell_type": "code",
139 |    "execution_count": null,
140 |    "metadata": {},
141 |    "outputs": [],
142 |    "source": [
143 |     "# Ваш код"
144 |    ]
145 |   },
146 |   {
147 |    "cell_type": "markdown",
148 |    "metadata": {},
149 |    "source": [
150 |     "№3 Найдите количество, среднее, cреднеквадратическое отклонение, минимум и максимум для длины маршрута и цены за поездку? Ответ округлите до 1 знака после запятой. Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.describe.html?highlight=describe#pyspark-sql-dataframe-describe\">describe</a>"
151 |    ]
152 |   },
153 |   {
154 |    "cell_type": "code",
155 |    "execution_count": null,
156 |    "metadata": {},
157 |    "outputs": [],
158 |    "source": [
159 |     "# Ваш код"
160 |    ]
161 |   },
162 |   {
163 |    "cell_type": "markdown",
164 |    "metadata": {},
165 |    "source": [
166 |     "№4 Найдите самый НЕпопулярный вид оплаты.\n",
167 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.groupBy.html?highlight=groupby#pyspark-sql-dataframe-groupby\">groupBy</a> <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.orderBy.html?highlight=orderby#pyspark-sql-dataframe-orderby\">orderBy</a>"
168 |    ]
169 |   },
170 |   {
171 |    "cell_type": "code",
172 |    "execution_count": null,
173 |    "metadata": {},
174 |    "outputs": [],
175 |    "source": [
176 |     "# Ваш код"
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "markdown",
181 |    "metadata": {},
182 |    "source": [
183 |     "№5 Найдите идентификатор таксиста выполнившего наибольшее число заказов."
184 |    ]
185 |   },
186 |   {
187 |    "cell_type": "code",
188 |    "execution_count": null,
189 |    "metadata": {},
190 |    "outputs": [],
191 |    "source": [
192 |     "# Ваш код"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "markdown",
197 |    "metadata": {},
198 |    "source": [
199 |     "№6 Чему равна средняя цена среди поездок, оплаченных наличными? Ответ округлите до 5 знака.\n",
200 |     "<br> Подробней <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.where.html?highlight=where#pyspark-sql-dataframe-where\">where</a>"
201 |    ]
202 |   },
203 |   {
204 |    "cell_type": "code",
205 |    "execution_count": null,
206 |    "metadata": {},
207 |    "outputs": [],
208 |    "source": [
209 |     "# Ваш код"
210 |    ]
211 |   },
212 |   {
213 |    "cell_type": "markdown",
214 |    "metadata": {},
215 |    "source": [
216 |     "№7 Сколько таксистов проехало больше 1000 миль за все время выполнения заказов?"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": null,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "# Ваш код"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "markdown",
230 |    "metadata": {},
231 |    "source": [
232 |     "№8 Сколько миль проехал пассажир в самой долгой поездке? (Ответ округлите до целого)"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": null,
238 |    "metadata": {},
239 |    "outputs": [],
240 |    "source": [
241 |     "# Ваш код"
242 |    ]
243 |   },
244 |   {
245 |    "cell_type": "markdown",
246 |    "metadata": {},
247 |    "source": [
248 |     "№9 Каков средний заработок всех таксистов? Ответ округлите до 5-ого знака.\n",
249 |     "<br>Отсеките неизвестные машины (не определенный taxi_id)."
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": null,
255 |    "metadata": {},
256 |    "outputs": [],
257 |    "source": [
258 |     "# Ваш код"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "markdown",
263 |    "metadata": {},
264 |    "source": [
265 |     "№10 Сколько поездок начиналось в самый загруженный час?\n",
266 |     "<br>Используйте функцию <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.hour.html?highlight=hour#pyspark-sql-functions-hour\">hour</a>"
267 |    ]
268 |   },
269 |   {
270 |    "cell_type": "code",
271 |    "execution_count": null,
272 |    "metadata": {},
273 |    "outputs": [],
274 |    "source": [
275 |     "from pyspark.sql.functions import hour"
276 |    ]
277 |   },
278 |   {
279 |    "cell_type": "code",
280 |    "execution_count": null,
281 |    "metadata": {},
282 |    "outputs": [],
283 |    "source": [
284 |     "# Ваш код"
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "markdown",
289 |    "metadata": {},
290 |    "source": [
291 |     "№11 Сколько поездок началось во второй четверти суток?"
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "code",
296 |    "execution_count": null,
297 |    "metadata": {},
298 |    "outputs": [],
299 |    "source": [
300 |     "# Ваш код"
301 |    ]
302 |   },
303 |   {
304 |    "cell_type": "markdown",
305 |    "metadata": {},
306 |    "source": [
307 |     "№12 Найдите топ три даты, в которые было суммарно больше всего чаевых? (Чаевые выдаются после совершения поездки)\n",
308 |     "<br> Ожидаемый формат дат YYYY-MM-DD\n",
309 |     "<br>Вам может понадобится конвертация типов <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.Column.cast.html?highlight=cast#pyspark-sql-column-cast\">cast</a>"
310 |    ]
311 |   },
312 |   {
313 |    "cell_type": "code",
314 |    "execution_count": null,
315 |    "metadata": {},
316 |    "outputs": [],
317 |    "source": [
318 |     "from pyspark.sql.types import DateType"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": null,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "# Ваш код"
328 |    ]
329 |   },
330 |   {
331 |    "cell_type": "markdown",
332 |    "metadata": {},
333 |    "source": [
334 |     "№13 Сколько было заказов в дату с наибольшим спросом?"
335 |    ]
336 |   },
337 |   {
338 |    "cell_type": "code",
339 |    "execution_count": null,
340 |    "metadata": {},
341 |    "outputs": [],
342 |    "source": [
343 |     "# Ваш код"
344 |    ]
345 |   },
346 |   {
347 |    "cell_type": "markdown",
348 |    "metadata": {},
349 |    "source": [
350 |     "Подгрузите данные о марках машин из датасета <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week3/spark-tasks/taxi_cars_data.parquet\">taxi_cars_data.parquet</a>"
351 |    ]
352 |   },
353 |   {
354 |    "cell_type": "code",
355 |    "execution_count": null,
356 |    "metadata": {},
357 |    "outputs": [],
358 |    "source": [
359 |     "df_car = # Ваш код загрузки"
360 |    ]
361 |   },
362 |   {
363 |    "cell_type": "code",
364 |    "execution_count": null,
365 |    "metadata": {},
366 |    "outputs": [],
367 |    "source": [
368 |     "df_car.show()"
369 |    ]
370 |   },
371 |   {
372 |    "cell_type": "markdown",
373 |    "metadata": {},
374 |    "source": [
375 |     "№14 Какая марка машины самая распрастранненая среди таксистов?\n",
376 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.split.html?highlight=split#pyspark-sql-functions-split\">split</a>"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": null,
382 |    "metadata": {},
383 |    "outputs": [],
384 |    "source": [
385 |     "from pyspark.sql.functions import split"
386 |    ]
387 |   },
388 |   {
389 |    "cell_type": "code",
390 |    "execution_count": null,
391 |    "metadata": {},
392 |    "outputs": [],
393 |    "source": [
394 |     "# Ваш код"
395 |    ]
396 |   },
397 |   {
398 |    "cell_type": "markdown",
399 |    "metadata": {},
400 |    "source": [
401 |     "№15 Сколько раз и какая модель машин чаще всего встречается в поездках?\n",
402 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.split.html?highlight=split#pyspark-sql-functions-split\">join</a>"
403 |    ]
404 |   },
405 |   {
406 |    "cell_type": "code",
407 |    "execution_count": null,
408 |    "metadata": {},
409 |    "outputs": [],
410 |    "source": [
411 |     "# Ваш код"
412 |    ]
413 |   },
414 |   {
415 |    "cell_type": "markdown",
416 |    "metadata": {},
417 |    "source": [
418 |     "Почувствуй силу сжатия! сохрани DataFrame в csv и сравни размеры файлов."
419 |    ]
420 |   },
421 |   {
422 |    "cell_type": "code",
423 |    "execution_count": null,
424 |    "metadata": {},
425 |    "outputs": [],
426 |    "source": [
427 |     "# Ваш код с coalesce(1)"
428 |    ]
429 |   },
430 |   {
431 |    "cell_type": "markdown",
432 |    "metadata": {},
433 |    "source": [
434 |     "Теперь загрузите данные из csv и проверьте типы методом printSchema()."
435 |    ]
436 |   },
437 |   {
438 |    "cell_type": "code",
439 |    "execution_count": null,
440 |    "metadata": {},
441 |    "outputs": [],
442 |    "source": [
443 |     "# Ваш код с printSchema() для DataFrame из csv"
444 |    ]
445 |   },
446 |   {
447 |    "cell_type": "markdown",
448 |    "metadata": {},
449 |    "source": [
450 |     "Не забудьте посетить SparkUI и изучить историю ваших задач."
451 |    ]
452 |   },
453 |   {
454 |    "cell_type": "code",
455 |    "execution_count": null,
456 |    "metadata": {},
457 |    "outputs": [],
458 |    "source": [
459 |     "spark"
460 |    ]
461 |   },
462 |   {
463 |    "cell_type": "code",
464 |    "execution_count": null,
465 |    "metadata": {},
466 |    "outputs": [],
467 |    "source": []
468 |   }
469 |  ],
470 |  "metadata": {
471 |   "kernelspec": {
472 |    "display_name": "Python 3",
473 |    "language": "python",
474 |    "name": "python3"
475 |   },
476 |   "language_info": {
477 |    "codemirror_mode": {
478 |     "name": "ipython",
479 |     "version": 3
480 |    },
481 |    "file_extension": ".py",
482 |    "mimetype": "text/x-python",
483 |    "name": "python",
484 |    "nbconvert_exporter": "python",
485 |    "pygments_lexer": "ipython3",
486 |    "version": "3.7.4"
487 |   }
488 |  },
489 |  "nbformat": 4,
490 |  "nbformat_minor": 2
491 | }
492 | 


--------------------------------------------------------------------------------
/Week3/Jupyter/notebooks/taxi_cars_data.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week3/Jupyter/notebooks/taxi_cars_data.parquet


--------------------------------------------------------------------------------
/Week3/Jupyter/notebooks/taxi_data.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week3/Jupyter/notebooks/taxi_data.parquet


--------------------------------------------------------------------------------
/Week3/Project/PySparkJob.py:
--------------------------------------------------------------------------------
 1 | import io
 2 | import sys
 3 | from pyspark.sql import SparkSession
 4 | from pyspark.sql.functions import col, datediff
 5 | from pyspark.sql import functions as F
 6 | 
 7 | 
 8 | def process(spark, input_file, target_path):
 9 |     # TODO Ваш код
10 | 
11 | 
12 | def main(argv):
13 |     input_path = argv[0]
14 |     print("Input path to file: " + input_path)
15 |     target_path = argv[1]
16 |     print("Target path: " + target_path)
17 |     spark = _spark_session()
18 |     process(spark, input_path, target_path)
19 | 
20 | 
21 | def _spark_session():
22 |     return SparkSession.builder.appName('PySparkJob').getOrCreate()
23 | 
24 | 
25 | if __name__ == "__main__":
26 |     arg = sys.argv[1:]
27 |     if len(arg) != 2:
28 |         sys.exit("Input and Target path are require.")
29 |     else:
30 |         main(arg)
31 | 


--------------------------------------------------------------------------------
/Week3/Project/clickstream.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week3/Project/clickstream.parquet


--------------------------------------------------------------------------------
/Week3/help.txt:
--------------------------------------------------------------------------------
 1 | Для работы необходимы:
 2 | 1) Python 3.X+
 3 | 2) Jupyter Notebook
 4 | 3) PySpark
 5 | pip install pyspark
 6 | 
 7 | Или используйте docker конфигурацию в папке Jupyter
 8 | 1) cd Jupyter
 9 | 2) docker-compose up
10 | 


--------------------------------------------------------------------------------
/Week3/spark-practice/PySparkTitanikJob.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "from pyspark.sql import SparkSession\n",
 10 |     "from pyspark.sql.functions import split,col,avg"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "metadata": {},
 17 |    "outputs": [],
 18 |    "source": [
 19 |     "spark = SparkSession.builder.appName('PySparkTitanikJob').getOrCreate()"
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "code",
 24 |    "execution_count": 3,
 25 |    "metadata": {},
 26 |    "outputs": [
 27 |     {
 28 |      "data": {
 29 |       "text/html": [
 30 |        "\n",
 31 |        "            <div>\n",
 32 |        "                <p><b>SparkSession - in-memory</b></p>\n",
 33 |        "                \n",
 34 |        "        <div>\n",
 35 |        "            <p><b>SparkContext</b></p>\n",
 36 |        "\n",
 37 |        "            <p><a href=\"http://unit-409.times.labs.intellij.net:4040\">Spark UI</a></p>\n",
 38 |        "\n",
 39 |        "            <dl>\n",
 40 |        "              <dt>Version</dt>\n",
 41 |        "                <dd><code>v2.4.3</code></dd>\n",
 42 |        "              <dt>Master</dt>\n",
 43 |        "                <dd><code>local[*]</code></dd>\n",
 44 |        "              <dt>AppName</dt>\n",
 45 |        "                <dd><code>PySparkTitanikJob</code></dd>\n",
 46 |        "            </dl>\n",
 47 |        "        </div>\n",
 48 |        "        \n",
 49 |        "            </div>\n",
 50 |        "        "
 51 |       ],
 52 |       "text/plain": [
 53 |        "<pyspark.sql.session.SparkSession at 0x7f07b46b9588>"
 54 |       ]
 55 |      },
 56 |      "execution_count": 3,
 57 |      "metadata": {},
 58 |      "output_type": "execute_result"
 59 |     }
 60 |    ],
 61 |    "source": [
 62 |     "spark"
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "code",
 67 |    "execution_count": 9,
 68 |    "metadata": {},
 69 |    "outputs": [],
 70 |    "source": [
 71 |     "df = spark.read.option('header','true').csv('train.csv')"
 72 |    ]
 73 |   },
 74 |   {
 75 |    "cell_type": "code",
 76 |    "execution_count": 10,
 77 |    "metadata": {},
 78 |    "outputs": [
 79 |     {
 80 |      "name": "stdout",
 81 |      "output_type": "stream",
 82 |      "text": [
 83 |       "+-----------+--------+------+--------------------+------+---+-----+-----+---------+-------+-----+--------+\n",
 84 |       "|PassengerId|Survived|Pclass|                Name|   Sex|Age|SibSp|Parch|   Ticket|   Fare|Cabin|Embarked|\n",
 85 |       "+-----------+--------+------+--------------------+------+---+-----+-----+---------+-------+-----+--------+\n",
 86 |       "|          1|       0|     3|Braund, Mr. Owen ...|  male| 22|    1|    0|A/5 21171|   7.25| null|       S|\n",
 87 |       "|          2|       1|     1|Cumings, Mrs. Joh...|female| 38|    1|    0| PC 17599|71.2833|  C85|       C|\n",
 88 |       "+-----------+--------+------+--------------------+------+---+-----+-----+---------+-------+-----+--------+\n",
 89 |       "only showing top 2 rows\n",
 90 |       "\n"
 91 |      ]
 92 |     }
 93 |    ],
 94 |    "source": [
 95 |     "df.show(2)"
 96 |    ]
 97 |   },
 98 |   {
 99 |    "cell_type": "code",
100 |    "execution_count": 15,
101 |    "metadata": {},
102 |    "outputs": [
103 |     {
104 |      "data": {
105 |       "text/plain": [
106 |        "[('PassengerId', 'string'),\n",
107 |        " ('Survived', 'string'),\n",
108 |        " ('Pclass', 'string'),\n",
109 |        " ('Name', 'string'),\n",
110 |        " ('Sex', 'string'),\n",
111 |        " ('Age', 'string'),\n",
112 |        " ('SibSp', 'string'),\n",
113 |        " ('Parch', 'string'),\n",
114 |        " ('Ticket', 'string'),\n",
115 |        " ('Fare', 'string'),\n",
116 |        " ('Cabin', 'string'),\n",
117 |        " ('Embarked', 'string')]"
118 |       ]
119 |      },
120 |      "execution_count": 15,
121 |      "metadata": {},
122 |      "output_type": "execute_result"
123 |     }
124 |    ],
125 |    "source": [
126 |     "df.dtypes"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "code",
131 |    "execution_count": 16,
132 |    "metadata": {},
133 |    "outputs": [
134 |     {
135 |      "name": "stdout",
136 |      "output_type": "stream",
137 |      "text": [
138 |       "+-------+------+------------------+\n",
139 |       "|summary|   Sex|               Age|\n",
140 |       "+-------+------+------------------+\n",
141 |       "|  count|   891|               714|\n",
142 |       "|   mean|  null| 29.69911764705882|\n",
143 |       "| stddev|  null|14.526497332334035|\n",
144 |       "|    min|female|              0.42|\n",
145 |       "|    max|  male|                 9|\n",
146 |       "+-------+------+------------------+\n",
147 |       "\n"
148 |      ]
149 |     }
150 |    ],
151 |    "source": [
152 |     "df.describe(['Sex', 'Age']).show()"
153 |    ]
154 |   },
155 |   {
156 |    "cell_type": "code",
157 |    "execution_count": 17,
158 |    "metadata": {},
159 |    "outputs": [
160 |     {
161 |      "data": {
162 |       "text/plain": [
163 |        "891"
164 |       ]
165 |      },
166 |      "execution_count": 17,
167 |      "metadata": {},
168 |      "output_type": "execute_result"
169 |     }
170 |    ],
171 |    "source": [
172 |     "df.count()"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "code",
177 |    "execution_count": 18,
178 |    "metadata": {},
179 |    "outputs": [],
180 |    "source": [
181 |     "df = df.drop('Ticket', 'Name', 'Fare','Cabin')"
182 |    ]
183 |   },
184 |   {
185 |    "cell_type": "code",
186 |    "execution_count": 19,
187 |    "metadata": {},
188 |    "outputs": [
189 |     {
190 |      "name": "stdout",
191 |      "output_type": "stream",
192 |      "text": [
193 |       "+-----------+--------+------+------+----+-----+-----+--------+\n",
194 |       "|PassengerId|Survived|Pclass|   Sex| Age|SibSp|Parch|Embarked|\n",
195 |       "+-----------+--------+------+------+----+-----+-----+--------+\n",
196 |       "|          1|       0|     3|  male|  22|    1|    0|       S|\n",
197 |       "|          2|       1|     1|female|  38|    1|    0|       C|\n",
198 |       "|          3|       1|     3|female|  26|    0|    0|       S|\n",
199 |       "|          4|       1|     1|female|  35|    1|    0|       S|\n",
200 |       "|          5|       0|     3|  male|  35|    0|    0|       S|\n",
201 |       "|          6|       0|     3|  male|null|    0|    0|       Q|\n",
202 |       "|          7|       0|     1|  male|  54|    0|    0|       S|\n",
203 |       "|          8|       0|     3|  male|   2|    3|    1|       S|\n",
204 |       "|          9|       1|     3|female|  27|    0|    2|       S|\n",
205 |       "|         10|       1|     2|female|  14|    1|    0|       C|\n",
206 |       "|         11|       1|     3|female|   4|    1|    1|       S|\n",
207 |       "|         12|       1|     1|female|  58|    0|    0|       S|\n",
208 |       "|         13|       0|     3|  male|  20|    0|    0|       S|\n",
209 |       "|         14|       0|     3|  male|  39|    1|    5|       S|\n",
210 |       "|         15|       0|     3|female|  14|    0|    0|       S|\n",
211 |       "|         16|       1|     2|female|  55|    0|    0|       S|\n",
212 |       "|         17|       0|     3|  male|   2|    4|    1|       Q|\n",
213 |       "|         18|       1|     2|  male|null|    0|    0|       S|\n",
214 |       "|         19|       0|     3|female|  31|    1|    0|       S|\n",
215 |       "|         20|       1|     3|female|null|    0|    0|       C|\n",
216 |       "+-----------+--------+------+------+----+-----+-----+--------+\n",
217 |       "only showing top 20 rows\n",
218 |       "\n"
219 |      ]
220 |     }
221 |    ],
222 |    "source": [
223 |     "df.show()"
224 |    ]
225 |   },
226 |   {
227 |    "cell_type": "code",
228 |    "execution_count": 28,
229 |    "metadata": {},
230 |    "outputs": [],
231 |    "source": [
232 |     "df = df.withColumn('FamilySize', col('SibSp') + col('Parch') + 1)"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": 29,
238 |    "metadata": {},
239 |    "outputs": [
240 |     {
241 |      "name": "stdout",
242 |      "output_type": "stream",
243 |      "text": [
244 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+\n",
245 |       "|PassengerId|Survived|Pclass|   Sex|Age|SibSp|Parch|Embarked|FamilySize|\n",
246 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+\n",
247 |       "|          1|       0|     3|  male| 22|    1|    0|       S|       2.0|\n",
248 |       "|          2|       1|     1|female| 38|    1|    0|       C|       2.0|\n",
249 |       "|          3|       1|     3|female| 26|    0|    0|       S|       1.0|\n",
250 |       "|          4|       1|     1|female| 35|    1|    0|       S|       2.0|\n",
251 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+\n",
252 |       "only showing top 4 rows\n",
253 |       "\n"
254 |      ]
255 |     }
256 |    ],
257 |    "source": [
258 |     "df.show(4)"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "code",
263 |    "execution_count": 30,
264 |    "metadata": {},
265 |    "outputs": [
266 |     {
267 |      "data": {
268 |       "text/plain": [
269 |        "177"
270 |       ]
271 |      },
272 |      "execution_count": 30,
273 |      "metadata": {},
274 |      "output_type": "execute_result"
275 |     }
276 |    ],
277 |    "source": [
278 |     "df.where(col('Age').isNull()).count()"
279 |    ]
280 |   },
281 |   {
282 |    "cell_type": "code",
283 |    "execution_count": 33,
284 |    "metadata": {},
285 |    "outputs": [],
286 |    "source": [
287 |     "avg_age = df.select(avg(col('Age'))).collect()[0][0]"
288 |    ]
289 |   },
290 |   {
291 |    "cell_type": "code",
292 |    "execution_count": 36,
293 |    "metadata": {},
294 |    "outputs": [],
295 |    "source": [
296 |     "ndf = df.fillna({'Age': avg_age})"
297 |    ]
298 |   },
299 |   {
300 |    "cell_type": "code",
301 |    "execution_count": 37,
302 |    "metadata": {},
303 |    "outputs": [
304 |     {
305 |      "name": "stdout",
306 |      "output_type": "stream",
307 |      "text": [
308 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+\n",
309 |       "|PassengerId|Survived|Pclass|   Sex|Age|SibSp|Parch|Embarked|FamilySize|\n",
310 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+\n",
311 |       "|          1|       0|     3|  male| 22|    1|    0|       S|       2.0|\n",
312 |       "|          2|       1|     1|female| 38|    1|    0|       C|       2.0|\n",
313 |       "|          3|       1|     3|female| 26|    0|    0|       S|       1.0|\n",
314 |       "|          4|       1|     1|female| 35|    1|    0|       S|       2.0|\n",
315 |       "|          5|       0|     3|  male| 35|    0|    0|       S|       1.0|\n",
316 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+\n",
317 |       "only showing top 5 rows\n",
318 |       "\n"
319 |      ]
320 |     }
321 |    ],
322 |    "source": [
323 |     "ndf.show(5)"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 43,
329 |    "metadata": {},
330 |    "outputs": [
331 |     {
332 |      "name": "stdout",
333 |      "output_type": "stream",
334 |      "text": [
335 |       "+------+\n",
336 |       "|   Sex|\n",
337 |       "+------+\n",
338 |       "|female|\n",
339 |       "|  male|\n",
340 |       "+------+\n",
341 |       "\n"
342 |      ]
343 |     }
344 |    ],
345 |    "source": [
346 |     "ndf[['Sex']].distinct().show()"
347 |    ]
348 |   },
349 |   {
350 |    "cell_type": "code",
351 |    "execution_count": 44,
352 |    "metadata": {},
353 |    "outputs": [],
354 |    "source": [
355 |     "ndf = ndf.withColumn('M', col('Sex') == 'male')"
356 |    ]
357 |   },
358 |   {
359 |    "cell_type": "code",
360 |    "execution_count": 45,
361 |    "metadata": {},
362 |    "outputs": [],
363 |    "source": [
364 |     "ndf = ndf.withColumn('W', col('Sex') == 'female')"
365 |    ]
366 |   },
367 |   {
368 |    "cell_type": "code",
369 |    "execution_count": 46,
370 |    "metadata": {},
371 |    "outputs": [
372 |     {
373 |      "name": "stdout",
374 |      "output_type": "stream",
375 |      "text": [
376 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+-----+-----+\n",
377 |       "|PassengerId|Survived|Pclass|   Sex|Age|SibSp|Parch|Embarked|FamilySize|    M|    W|\n",
378 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+-----+-----+\n",
379 |       "|          1|       0|     3|  male| 22|    1|    0|       S|       2.0| true|false|\n",
380 |       "|          2|       1|     1|female| 38|    1|    0|       C|       2.0|false| true|\n",
381 |       "+-----------+--------+------+------+---+-----+-----+--------+----------+-----+-----+\n",
382 |       "only showing top 2 rows\n",
383 |       "\n"
384 |      ]
385 |     }
386 |    ],
387 |    "source": [
388 |     "ndf.show(2)"
389 |    ]
390 |   },
391 |   {
392 |    "cell_type": "code",
393 |    "execution_count": 47,
394 |    "metadata": {},
395 |    "outputs": [],
396 |    "source": [
397 |     "ndf = ndf.drop('Sex')"
398 |    ]
399 |   },
400 |   {
401 |    "cell_type": "code",
402 |    "execution_count": 48,
403 |    "metadata": {},
404 |    "outputs": [
405 |     {
406 |      "name": "stdout",
407 |      "output_type": "stream",
408 |      "text": [
409 |       "+-----------+--------+------+---+-----+-----+--------+----------+-----+-----+\n",
410 |       "|PassengerId|Survived|Pclass|Age|SibSp|Parch|Embarked|FamilySize|    M|    W|\n",
411 |       "+-----------+--------+------+---+-----+-----+--------+----------+-----+-----+\n",
412 |       "|          1|       0|     3| 22|    1|    0|       S|       2.0| true|false|\n",
413 |       "|          2|       1|     1| 38|    1|    0|       C|       2.0|false| true|\n",
414 |       "|          3|       1|     3| 26|    0|    0|       S|       1.0|false| true|\n",
415 |       "|          4|       1|     1| 35|    1|    0|       S|       2.0|false| true|\n",
416 |       "|          5|       0|     3| 35|    0|    0|       S|       1.0| true|false|\n",
417 |       "+-----------+--------+------+---+-----+-----+--------+----------+-----+-----+\n",
418 |       "only showing top 5 rows\n",
419 |       "\n"
420 |      ]
421 |     }
422 |    ],
423 |    "source": [
424 |     "ndf.show(5)"
425 |    ]
426 |   },
427 |   {
428 |    "cell_type": "code",
429 |    "execution_count": 51,
430 |    "metadata": {},
431 |    "outputs": [],
432 |    "source": [
433 |     "ndf.coalesce(1).write.option('header','true').csv('clear_data')"
434 |    ]
435 |   },
436 |   {
437 |    "cell_type": "code",
438 |    "execution_count": null,
439 |    "metadata": {},
440 |    "outputs": [],
441 |    "source": []
442 |   }
443 |  ],
444 |  "metadata": {
445 |   "kernelspec": {
446 |    "display_name": "Python 3",
447 |    "language": "python",
448 |    "name": "python3"
449 |   },
450 |   "language_info": {
451 |    "codemirror_mode": {
452 |     "name": "ipython",
453 |     "version": 3
454 |    },
455 |    "file_extension": ".py",
456 |    "mimetype": "text/x-python",
457 |    "name": "python",
458 |    "nbconvert_exporter": "python",
459 |    "pygments_lexer": "ipython3",
460 |    "version": "3.6.5"
461 |   }
462 |  },
463 |  "nbformat": 4,
464 |  "nbformat_minor": 2
465 | }
466 | 


--------------------------------------------------------------------------------
/Week3/spark-tasks/PySparkTasksTemplate.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#   @@@@@@@     @      @    @  @   #\n",
 10 |     "#   @  @  @    @ @      @  @       #\n",
 11 |     "#      @  @   @   @      @@    @   #\n",
 12 |     "#      @     @@@@@@@    @  @   @   #\n",
 13 |     "#      @    @       @  @    @  @   #"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "markdown",
 18 |    "metadata": {},
 19 |    "source": [
 20 |     "Привет, в этой практике мы с вами применим наши знания по PySpark и постараемся изучить что-то новое в процессе выполнения.\n",
 21 |     "<br>В занятии используется датасет собранный на основе данных <a href=\"https://www.kaggle.com/chicago/chicago-taxi-rides-2016\">Chicago Taxi Rides 2016</a>\n",
 22 |     "<br>Полная <a href=\"https://spark.apache.org/docs/latest/api/python/index.html\">документация PySpark</a>.\n",
 23 |     "<br>Схема данны:\n",
 24 |     "<br>|-- taxi_id = идентификатор таксиста\n",
 25 |     "<br>|-- trip_start_timestamp = время начала поездки\n",
 26 |     "<br>|-- trip_end_timestamp = время окончания поездки\n",
 27 |     "<br>|-- trip_seconds = время длительности поездки в секундах\n",
 28 |     "<br>|-- trip_miles = мили проиденные во время поездки\n",
 29 |     "<br>|-- fare = транспортные расходы\n",
 30 |     "<br>|-- tips = назначенные чаевые\n",
 31 |     "<br>|-- trip_total = общая стоимость поездки (Итоговая с учетом чаевых и расходов)\n",
 32 |     "<br>|-- payment_type = тип оплаты"
 33 |    ]
 34 |   },
 35 |   {
 36 |    "cell_type": "code",
 37 |    "execution_count": null,
 38 |    "metadata": {},
 39 |    "outputs": [],
 40 |    "source": [
 41 |     "from pyspark.sql import SparkSession\n",
 42 |     "from pyspark.sql.functions import col"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": null,
 48 |    "metadata": {},
 49 |    "outputs": [],
 50 |    "source": [
 51 |     "spark = SparkSession.builder.appName('PySparkTasks').getOrCreate()"
 52 |    ]
 53 |   },
 54 |   {
 55 |    "cell_type": "code",
 56 |    "execution_count": null,
 57 |    "metadata": {},
 58 |    "outputs": [],
 59 |    "source": [
 60 |     "spark.conf.set(\"spark.sql.session.timeZone\", \"GMT+3\")"
 61 |    ]
 62 |   },
 63 |   {
 64 |    "cell_type": "code",
 65 |    "execution_count": null,
 66 |    "metadata": {},
 67 |    "outputs": [],
 68 |    "source": [
 69 |     "spark"
 70 |    ]
 71 |   },
 72 |   {
 73 |    "cell_type": "markdown",
 74 |    "metadata": {},
 75 |    "source": [
 76 |     "Скачайте <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week3/spark-tasks/taxi_data.parquet\">taxi_data.parquet</a> и загрузите используя <a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark.sql.DataFrame\">SparkAPI</a>"
 77 |    ]
 78 |   },
 79 |   {
 80 |    "cell_type": "code",
 81 |    "execution_count": null,
 82 |    "metadata": {},
 83 |    "outputs": [],
 84 |    "source": [
 85 |     "df = #Ваш код загрузки"
 86 |    ]
 87 |   },
 88 |   {
 89 |    "cell_type": "markdown",
 90 |    "metadata": {},
 91 |    "source": [
 92 |     "№1 Посчитайте количество загруженных строк."
 93 |    ]
 94 |   },
 95 |   {
 96 |    "cell_type": "code",
 97 |    "execution_count": null,
 98 |    "metadata": {},
 99 |    "outputs": [],
100 |    "source": [
101 |     "# Число строк"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": null,
107 |    "metadata": {},
108 |    "outputs": [],
109 |    "source": [
110 |     "df.show()"
111 |    ]
112 |   },
113 |   {
114 |    "cell_type": "markdown",
115 |    "metadata": {},
116 |    "source": [
117 |     "Посмотрим схему данных:"
118 |    ]
119 |   },
120 |   {
121 |    "cell_type": "code",
122 |    "execution_count": null,
123 |    "metadata": {},
124 |    "outputs": [],
125 |    "source": [
126 |     "df.printSchema()"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "markdown",
131 |    "metadata": {},
132 |    "source": [
133 |     "№2 Чему равна корреляция и ковариация между длиной маршрута и ценой за поездку? Ответ округлите до 5 знаков после запятой.\n",
134 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.corr.html?highlight=corr#pyspark-sql-dataframe-corr\">corr</a> & <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.cov.html?highlight=cov#pyspark-sql-dataframe-cov\">cov</a>"
135 |    ]
136 |   },
137 |   {
138 |    "cell_type": "code",
139 |    "execution_count": null,
140 |    "metadata": {},
141 |    "outputs": [],
142 |    "source": [
143 |     "# Ваш код"
144 |    ]
145 |   },
146 |   {
147 |    "cell_type": "markdown",
148 |    "metadata": {},
149 |    "source": [
150 |     "№3 Найдите количество, среднее, cреднеквадратическое отклонение, минимум и максимум для длины маршрута и цены за поездку? Ответ округлите до 1 знака после запятой. Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.describe.html?highlight=describe#pyspark-sql-dataframe-describe\">describe</a>"
151 |    ]
152 |   },
153 |   {
154 |    "cell_type": "code",
155 |    "execution_count": null,
156 |    "metadata": {},
157 |    "outputs": [],
158 |    "source": [
159 |     "# Ваш код"
160 |    ]
161 |   },
162 |   {
163 |    "cell_type": "markdown",
164 |    "metadata": {},
165 |    "source": [
166 |     "№4 Найдите самый НЕпопулярный вид оплаты.\n",
167 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.groupBy.html?highlight=groupby#pyspark-sql-dataframe-groupby\">groupBy</a> <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.orderBy.html?highlight=orderby#pyspark-sql-dataframe-orderby\">orderBy</a>"
168 |    ]
169 |   },
170 |   {
171 |    "cell_type": "code",
172 |    "execution_count": null,
173 |    "metadata": {},
174 |    "outputs": [],
175 |    "source": [
176 |     "# Ваш код"
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "markdown",
181 |    "metadata": {},
182 |    "source": [
183 |     "№5 Найдите идентификатор таксиста выполнившего наибольшее число заказов."
184 |    ]
185 |   },
186 |   {
187 |    "cell_type": "code",
188 |    "execution_count": null,
189 |    "metadata": {},
190 |    "outputs": [],
191 |    "source": [
192 |     "# Ваш код"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "markdown",
197 |    "metadata": {},
198 |    "source": [
199 |     "№6 Чему равна средняя цена среди поездок, оплаченных наличными? Ответ округлите до 5 знака.\n",
200 |     "<br> Подробней <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.DataFrame.where.html?highlight=where#pyspark-sql-dataframe-where\">where</a>"
201 |    ]
202 |   },
203 |   {
204 |    "cell_type": "code",
205 |    "execution_count": null,
206 |    "metadata": {},
207 |    "outputs": [],
208 |    "source": [
209 |     "# Ваш код"
210 |    ]
211 |   },
212 |   {
213 |    "cell_type": "markdown",
214 |    "metadata": {},
215 |    "source": [
216 |     "№7 Сколько таксистов проехало больше 1000 миль за все время выполнения заказов?"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": null,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "# Ваш код"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "markdown",
230 |    "metadata": {},
231 |    "source": [
232 |     "№8 Сколько миль проехал пассажир в самой долгой поездке? (Ответ округлите до целого)"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": null,
238 |    "metadata": {},
239 |    "outputs": [],
240 |    "source": [
241 |     "# Ваш код"
242 |    ]
243 |   },
244 |   {
245 |    "cell_type": "markdown",
246 |    "metadata": {},
247 |    "source": [
248 |     "№9 Каков средний заработок всех таксистов? Ответ округлите до 5-ого знака.\n",
249 |     "<br>Отсеките неизвестные машины (не определенный taxi_id)."
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": null,
255 |    "metadata": {},
256 |    "outputs": [],
257 |    "source": [
258 |     "# Ваш код"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "markdown",
263 |    "metadata": {},
264 |    "source": [
265 |     "№10 Сколько поездок начиналось в самый загруженный час?\n",
266 |     "<br>Используйте функцию <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.hour.html?highlight=hour#pyspark-sql-functions-hour\">hour</a>"
267 |    ]
268 |   },
269 |   {
270 |    "cell_type": "code",
271 |    "execution_count": null,
272 |    "metadata": {},
273 |    "outputs": [],
274 |    "source": [
275 |     "from pyspark.sql.functions import hour"
276 |    ]
277 |   },
278 |   {
279 |    "cell_type": "code",
280 |    "execution_count": null,
281 |    "metadata": {},
282 |    "outputs": [],
283 |    "source": [
284 |     "# Ваш код"
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "markdown",
289 |    "metadata": {},
290 |    "source": [
291 |     "№11 Сколько поездок началось во второй четверти суток?"
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "code",
296 |    "execution_count": null,
297 |    "metadata": {},
298 |    "outputs": [],
299 |    "source": [
300 |     "# Ваш код"
301 |    ]
302 |   },
303 |   {
304 |    "cell_type": "markdown",
305 |    "metadata": {},
306 |    "source": [
307 |     "№12 Найдите топ три даты, в которые было суммарно больше всего чаевых? (Чаевые выдаются после совершения поездки)\n",
308 |     "<br> Ожидаемый формат дат YYYY-MM-DD\n",
309 |     "<br>Вам может понадобится конвертация типов <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.Column.cast.html?highlight=cast#pyspark-sql-column-cast\">cast</a>"
310 |    ]
311 |   },
312 |   {
313 |    "cell_type": "code",
314 |    "execution_count": null,
315 |    "metadata": {},
316 |    "outputs": [],
317 |    "source": [
318 |     "from pyspark.sql.types import DateType"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": null,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "# Ваш код"
328 |    ]
329 |   },
330 |   {
331 |    "cell_type": "markdown",
332 |    "metadata": {},
333 |    "source": [
334 |     "№13 Сколько было заказов в дату с наибольшим спросом?"
335 |    ]
336 |   },
337 |   {
338 |    "cell_type": "code",
339 |    "execution_count": null,
340 |    "metadata": {},
341 |    "outputs": [],
342 |    "source": [
343 |     "# Ваш код"
344 |    ]
345 |   },
346 |   {
347 |    "cell_type": "markdown",
348 |    "metadata": {},
349 |    "source": [
350 |     "Подгрузите данные о марках машин из датасета <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week3/spark-tasks/taxi_cars_data.parquet\">taxi_cars_data.parquet</a>"
351 |    ]
352 |   },
353 |   {
354 |    "cell_type": "code",
355 |    "execution_count": null,
356 |    "metadata": {},
357 |    "outputs": [],
358 |    "source": [
359 |     "df_car = # Ваш код загрузки"
360 |    ]
361 |   },
362 |   {
363 |    "cell_type": "code",
364 |    "execution_count": null,
365 |    "metadata": {},
366 |    "outputs": [],
367 |    "source": [
368 |     "df_car.show()"
369 |    ]
370 |   },
371 |   {
372 |    "cell_type": "markdown",
373 |    "metadata": {},
374 |    "source": [
375 |     "№14 Какая марка машины самая распрастранненая среди таксистов?\n",
376 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.split.html?highlight=split#pyspark-sql-functions-split\">split</a>"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": null,
382 |    "metadata": {},
383 |    "outputs": [],
384 |    "source": [
385 |     "from pyspark.sql.functions import split"
386 |    ]
387 |   },
388 |   {
389 |    "cell_type": "code",
390 |    "execution_count": null,
391 |    "metadata": {},
392 |    "outputs": [],
393 |    "source": [
394 |     "# Ваш код"
395 |    ]
396 |   },
397 |   {
398 |    "cell_type": "markdown",
399 |    "metadata": {},
400 |    "source": [
401 |     "№15 Сколько раз и какая модель машин чаще всего встречается в поездках?\n",
402 |     "<br>Подробнее <a href=\"https://spark.apache.org/docs/3.1.1/api/python/reference/api/pyspark.sql.functions.split.html?highlight=split#pyspark-sql-functions-split\">join</a>"
403 |    ]
404 |   },
405 |   {
406 |    "cell_type": "code",
407 |    "execution_count": null,
408 |    "metadata": {},
409 |    "outputs": [],
410 |    "source": [
411 |     "# Ваш код"
412 |    ]
413 |   },
414 |   {
415 |    "cell_type": "markdown",
416 |    "metadata": {},
417 |    "source": [
418 |     "Почувствуй силу сжатия! сохрани DataFrame в csv и сравни размеры файлов."
419 |    ]
420 |   },
421 |   {
422 |    "cell_type": "code",
423 |    "execution_count": null,
424 |    "metadata": {},
425 |    "outputs": [],
426 |    "source": [
427 |     "# Ваш код с coalesce(1)"
428 |    ]
429 |   },
430 |   {
431 |    "cell_type": "markdown",
432 |    "metadata": {},
433 |    "source": [
434 |     "Теперь загрузите данные из csv и проверьте типы методом printSchema()."
435 |    ]
436 |   },
437 |   {
438 |    "cell_type": "code",
439 |    "execution_count": null,
440 |    "metadata": {},
441 |    "outputs": [],
442 |    "source": [
443 |     "# Ваш код с printSchema() для DataFrame из csv"
444 |    ]
445 |   },
446 |   {
447 |    "cell_type": "markdown",
448 |    "metadata": {},
449 |    "source": [
450 |     "Не забудьте посетить SparkUI и изучить историю ваших задач."
451 |    ]
452 |   },
453 |   {
454 |    "cell_type": "code",
455 |    "execution_count": null,
456 |    "metadata": {},
457 |    "outputs": [],
458 |    "source": [
459 |     "spark"
460 |    ]
461 |   },
462 |   {
463 |    "cell_type": "code",
464 |    "execution_count": null,
465 |    "metadata": {},
466 |    "outputs": [],
467 |    "source": []
468 |   }
469 |  ],
470 |  "metadata": {
471 |   "kernelspec": {
472 |    "display_name": "Python 3",
473 |    "language": "python",
474 |    "name": "python3"
475 |   },
476 |   "language_info": {
477 |    "codemirror_mode": {
478 |     "name": "ipython",
479 |     "version": 3
480 |    },
481 |    "file_extension": ".py",
482 |    "mimetype": "text/x-python",
483 |    "name": "python",
484 |    "nbconvert_exporter": "python",
485 |    "pygments_lexer": "ipython3",
486 |    "version": "3.7.4"
487 |   }
488 |  },
489 |  "nbformat": 4,
490 |  "nbformat_minor": 2
491 | }
492 | 


--------------------------------------------------------------------------------
/Week3/spark-tasks/taxi_cars_data.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week3/spark-tasks/taxi_cars_data.parquet


--------------------------------------------------------------------------------
/Week3/spark-tasks/taxi_data.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week3/spark-tasks/taxi_data.parquet


--------------------------------------------------------------------------------
/Week4/Airflow/container-data/airflow/dags/calculate_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.models import Variable
 4 | from airflow.operators.python_operator import PythonOperator
 5 | 
 6 | 
 7 | def load():
 8 |     return int(Variable.get('value'))
 9 | 
10 | 
11 | def multiply(**ctx):
12 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='load_task')
13 |     x = x * 25
14 |     return x
15 | 
16 | 
17 | def plus(**ctx):
18 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='multiply_task')
19 |     x = x + 5
20 |     return x
21 | 
22 | 
23 | def upload(**ctx):
24 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='plus_task')
25 |     Variable.set('result', x)
26 | 
27 | 
28 | dag = DAG(dag_id='calculation-dag',
29 |           start_date=datetime(2020, 3, 30),
30 |           schedule_interval='@once')
31 | 
32 | load_task = PythonOperator(task_id='load_task',
33 |                            python_callable=load,
34 |                            dag=dag)
35 | multiply_task = PythonOperator(task_id='multiply_task',
36 |                                python_callable=multiply,
37 |                                provide_context=True,
38 |                                dag=dag)
39 | plus_task = PythonOperator(task_id='plus_task',
40 |                            python_callable=plus,
41 |                            provide_context=True,
42 |                            dag=dag)
43 | upload_task = PythonOperator(task_id='upload_task',
44 |                              python_callable=upload,
45 |                              provide_context=True,
46 |                              dag=dag)
47 | 
48 | 
49 | load_task >> multiply_task >> plus_task >> upload_task
50 | 


--------------------------------------------------------------------------------
/Week4/Airflow/container-data/airflow/dags/calculate_parallel_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.models import Variable
 4 | from airflow.operators.python_operator import PythonOperator
 5 | 
 6 | 
 7 | def load():
 8 |     return int(Variable.get('value'))
 9 | 
10 | 
11 | def multiply(**ctx):
12 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='load_task')
13 |     x = x * 25
14 |     return x
15 | 
16 | 
17 | def plus5(**ctx):
18 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='multiply_task')
19 |     x = x + 5
20 |     return x
21 | 
22 | 
23 | def plus10(**ctx):
24 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='multiply_task')
25 |     x = x + 10
26 |     return x
27 | 
28 | 
29 | def upload1(**ctx):
30 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='plus5_task')
31 |     Variable.set('result1', x)
32 | 
33 | 
34 | def upload2(**ctx):
35 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='plus10_task')
36 |     Variable.set('result2', x)
37 | 
38 | 
39 | dag = DAG(dag_id='calculation-parallel-dag',
40 |           start_date=datetime(2020, 3, 30),
41 |           schedule_interval='@once')
42 | 
43 | load_task = PythonOperator(task_id='load_task',
44 |                            python_callable=load,
45 |                            dag=dag)
46 | multiply_task = PythonOperator(task_id='multiply_task',
47 |                                python_callable=multiply,
48 |                                provide_context=True,
49 |                                dag=dag)
50 | plus5_task = PythonOperator(task_id='plus5_task',
51 |                             python_callable=plus5,
52 |                             provide_context=True,
53 |                             dag=dag)
54 | plus10_task = PythonOperator(task_id='plus10_task',
55 |                              python_callable=plus10,
56 |                              provide_context=True,
57 |                              dag=dag)
58 | upload1_task = PythonOperator(task_id='upload1_task',
59 |                               python_callable=upload1,
60 |                               provide_context=True,
61 |                               dag=dag)
62 | upload2_task = PythonOperator(task_id='upload2_task',
63 |                               python_callable=upload2,
64 |                               provide_context=True,
65 |                               dag=dag)
66 | 
67 | 
68 | load_task >> multiply_task
69 | multiply_task >> plus5_task >> upload1_task
70 | multiply_task >> plus10_task >> upload2_task
71 | 


--------------------------------------------------------------------------------
/Week4/Airflow/container-data/airflow/dags/dummy_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.operators.dummy_operator import DummyOperator
 4 | 
 5 | 
 6 | dag = DAG(dag_id='dummy-dag',
 7 |           start_date=datetime(2020, 3, 30),
 8 |           schedule_interval='@once')
 9 | 
10 | t1 = DummyOperator(task_id='task1', dag=dag)
11 | t2 = DummyOperator(task_id='task2', dag=dag)
12 | t3 = DummyOperator(task_id='task3', dag=dag)
13 | t4 = DummyOperator(task_id='task4', dag=dag)
14 | t5 = DummyOperator(task_id='task5', dag=dag)
15 | t6 = DummyOperator(task_id='task6', dag=dag)
16 | t7 = DummyOperator(task_id='task7', dag=dag)
17 | t8 = DummyOperator(task_id='task8', dag=dag)
18 | t9 = DummyOperator(task_id='task9', dag=dag)
19 | t10 = DummyOperator(task_id='task10', dag=dag)
20 | t11 = DummyOperator(task_id='task11', dag=dag)
21 | t12 = DummyOperator(task_id='task12', dag=dag)
22 | t13 = DummyOperator(task_id='task13', dag=dag)
23 | t14 = DummyOperator(task_id='task14', dag=dag)
24 | t15 = DummyOperator(task_id='task15', dag=dag)
25 | t16 = DummyOperator(task_id='task16', dag=dag)
26 | t17 = DummyOperator(task_id='task17', dag=dag)
27 | t18 = DummyOperator(task_id='task18', dag=dag)
28 | t19 = DummyOperator(task_id='task19', dag=dag)
29 | t20 = DummyOperator(task_id='task20', dag=dag)
30 | 
31 | t1 >> t2
32 | t2 >> t3 >> t5 >> t7
33 | t2 >> t4 >> t6 >> t7
34 | t2 >> t8 >> t7
35 | t2 >> t9 >> t7
36 | t7 >> t10
37 | t10 >> t11 >> t15
38 | t10 >> t12 >> t15
39 | t10 >> t13 >> t15
40 | t10 >> t14 >> t15
41 | t15 >> t16
42 | t16 >> t17
43 | t16 >> t18
44 | t16 >> t19
45 | t16 >> t20
46 | 


--------------------------------------------------------------------------------
/Week4/Airflow/container-data/airflow/dags/hello_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG, AirflowException
 3 | from datetime import datetime
 4 | from airflow.operators.python_operator import PythonOperator
 5 | from airflow.utils.trigger_rule import TriggerRule
 6 | 
 7 | 
 8 | def print_1():
 9 |     return 'Step 1'
10 | 
11 | 
12 | def print_2():
13 |     #raise AirflowException('Oops!') #Uncomment to make error
14 |     return 'Step 2'
15 | 
16 | 
17 | def print_3():
18 |     return 'Step 3'
19 | 
20 | 
21 | def print_hello():
22 |     return 'Hello Wolrd'
23 | 
24 | 
25 | dag = DAG('hello-world-dag',
26 |           start_date=datetime(2020, 3, 30),
27 |           description='Hello world example',
28 |           schedule_interval='@once')
29 | 
30 | step1 = PythonOperator(task_id='step1', python_callable=print_1, dag=dag)
31 | step2 = PythonOperator(task_id='step2', python_callable=print_2, dag=dag)
32 | step3 = PythonOperator(task_id='step3', python_callable=print_3, dag=dag)
33 | hello_operator = PythonOperator(task_id='hello_task',
34 |                                 python_callable=print_hello,
35 |                                 #trigger_rule=TriggerRule.ONE_SUCCESS, #Uncomment to skip error
36 |                                 dag=dag)
37 | 
38 | step1 >> [step2, step3]
39 | step2 >> hello_operator
40 | step3 >> hello_operator
41 | 


--------------------------------------------------------------------------------
/Week4/Airflow/docker-compose.yaml:
--------------------------------------------------------------------------------
 1 | version: '2.1'
 2 | services:
 3 |     redis:
 4 |         image: 'redis:5.0.5'
 5 |         # command: redis-server --requirepass redispass
 6 | 
 7 |     postgres:
 8 |         image: postgres:9.6
 9 |         environment:
10 |             - POSTGRES_USER=airflow
11 |             - POSTGRES_PASSWORD=airflow
12 |             - POSTGRES_DB=airflow
13 |         # Uncomment these lines to persist data on the local filesystem.
14 |         #     - PGDATA=/var/lib/postgresql/data/pgdata
15 |         # volumes:
16 |         #     - ./pgdata:/var/lib/postgresql/data/pgdata
17 | 
18 |     webserver:
19 |         image: puckel/docker-airflow:1.10.4
20 |         restart: always
21 |         depends_on:
22 |             - postgres
23 |             - redis
24 |         environment:
25 |             - LOAD_EX=n
26 |             - FERNET_KEY=46BKJoQYlPPOexq0OhDZnIlNepKFf87WFwLbfzqDDho=
27 |             - EXECUTOR=Celery
28 |             # - POSTGRES_USER=airflow
29 |             # - POSTGRES_PASSWORD=airflow
30 |             # - POSTGRES_DB=airflow
31 |             # - REDIS_PASSWORD=redispass
32 |         volumes:
33 |             - ./container-data/airflow/dags:/usr/local/airflow/dags
34 |             # Uncomment to include custom plugins
35 |             # - ./plugins:/usr/local/airflow/plugins
36 |         ports:
37 |             - "8080:8080"
38 |         command: webserver
39 |         healthcheck:
40 |             test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-webserver.pid ]"]
41 |             interval: 30s
42 |             timeout: 30s
43 |             retries: 3
44 | 
45 |     flower:
46 |         image: puckel/docker-airflow:1.10.4
47 |         restart: always
48 |         depends_on:
49 |             - redis
50 |         environment:
51 |             - EXECUTOR=Celery
52 |             # - REDIS_PASSWORD=redispass
53 |         ports:
54 |             - "5555:5555"
55 |         command: flower
56 | 
57 |     scheduler:
58 |         image: puckel/docker-airflow:1.10.4
59 |         restart: always
60 |         depends_on:
61 |             - webserver
62 |         volumes:
63 |             - ./container-data/airflow/dags:/usr/local/airflow/dags
64 |             # Uncomment to include custom plugins
65 |             # - ./plugins:/usr/local/airflow/plugins
66 |         environment:
67 |             - LOAD_EX=n
68 |             - FERNET_KEY=46BKJoQYlPPOexq0OhDZnIlNepKFf87WFwLbfzqDDho=
69 |             - EXECUTOR=Celery
70 |             # - POSTGRES_USER=airflow
71 |             # - POSTGRES_PASSWORD=airflow
72 |             # - POSTGRES_DB=airflow
73 |             # - REDIS_PASSWORD=redispass
74 |         command: scheduler
75 | 
76 |     worker:
77 |         image: puckel/docker-airflow:1.10.4
78 |         restart: always
79 |         depends_on:
80 |             - scheduler
81 |         volumes:
82 |             - ./container-data/airflow/dags:/usr/local/airflow/dags
83 |             # Uncomment to include custom plugins
84 |             # - ./plugins:/usr/local/airflow/plugins
85 |         environment:
86 |             - FERNET_KEY=46BKJoQYlPPOexq0OhDZnIlNepKFf87WFwLbfzqDDho=
87 |             - EXECUTOR=Celery
88 |             # - POSTGRES_USER=airflow
89 |             # - POSTGRES_PASSWORD=airflow
90 |             # - POSTGRES_DB=airflow
91 |             # - REDIS_PASSWORD=redispass
92 |         command: worker
93 | 


--------------------------------------------------------------------------------
/Week4/help.txt:
--------------------------------------------------------------------------------
 1 | Выполнять из папки Week4/Airflow
 2 | 1) Запуск контейнеров
 3 |     docker-compose up -d
 4 | 2) Проверка запущенных контейнеров
 5 |     docker ps
 6 | 3) UI Airflow
 7 |     http://localhost:8080
 8 | 4) DAGs которые подгружаются в Airflow Week4/Airflow/container-data/airflow/dags
 9 |    Вы можете менять их или добавлять свои не останавливая контейнер
10 | 5) Остановка контейнеров
11 |     docker-compose down


--------------------------------------------------------------------------------
/Week5/SparkML/Project/PySparkMLFit.py:
--------------------------------------------------------------------------------
 1 | import io
 2 | import sys
 3 | 
 4 | from pyspark.ml import Pipeline
 5 | from pyspark.ml.evaluation import RegressionEvaluator
 6 | from pyspark.ml.feature import VectorAssembler
 7 | from pyspark.ml.regression import LinearRegression
 8 | from pyspark.sql import SparkSession
 9 | 
10 | # Используйте как путь куда сохранить модель
11 | MODEL_PATH = 'spark_ml_model'
12 | 
13 | 
14 | def process(spark, train_data, test_data):
15 |     #train_data - путь к файлу с данными для обучения модели
16 |     #test_data - путь к файлу с данными для оценки качества модели
17 |     #Ваш код
18 | 
19 | 
20 | def main(argv):
21 |     train_data = argv[0]
22 |     print("Input path to train data: " + train_data)
23 |     test_data = argv[1]
24 |     print("Input path to test data: " + test_data)
25 |     spark = _spark_session()
26 |     process(spark, train_data, test_data)
27 | 
28 | 
29 | def _spark_session():
30 |     return SparkSession.builder.appName('PySparkMLFitJob').getOrCreate()
31 | 
32 | 
33 | if __name__ == "__main__":
34 |     arg = sys.argv[1:]
35 |     if len(arg) != 2:
36 |         sys.exit("Train and test data are require.")
37 |     else:
38 |         main(arg)
39 | 


--------------------------------------------------------------------------------
/Week5/SparkML/Project/PySparkMLPredict.py:
--------------------------------------------------------------------------------
 1 | import io
 2 | import sys
 3 | 
 4 | from pyspark.ml import PipelineModel
 5 | from pyspark.sql import SparkSession
 6 | 
 7 | # Используйте как путь откуда загрузить модель
 8 | MODEL_PATH = 'spark_ml_model'
 9 | 
10 | 
11 | def process(spark, input_file, output_file):
12 |     #input_file - путь к файлу с данными для которых нужно предсказать ctr
13 |     #output_file - путь по которому нужно сохранить файл с результатами [ads_id, prediction]
14 |     #Ваш код
15 | 
16 | 
17 | def main(argv):
18 |     input_path = argv[0]
19 |     print("Input path to file: " + input_path)
20 |     output_file = argv[1]
21 |     print("Output path to file: " + output_file)
22 |     spark = _spark_session()
23 |     process(spark, input_path, output_file)
24 | 
25 | 
26 | def _spark_session():
27 |     return SparkSession.builder.appName('PySparkMLPredict').getOrCreate()
28 | 
29 | 
30 | if __name__ == "__main__":
31 |     arg = sys.argv[1:]
32 |     if len(arg) != 2:
33 |         sys.exit("Input and Target path are require.")
34 |     else:
35 |         main(arg)
36 | 


--------------------------------------------------------------------------------
/Week5/SparkML/Project/test.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/Project/test.parquet


--------------------------------------------------------------------------------
/Week5/SparkML/Project/train.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/Project/train.parquet


--------------------------------------------------------------------------------
/Week5/SparkML/spark-practice/cat_dog/PySparkMLDL.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "!pip install sparkdl keras tensorflow==1.13.1 tensorframes==0.2.7 tensorflowonspark==1.3.0 jieba"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": 1,
 15 |    "metadata": {},
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "import os\n",
 19 |     "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"-1\"  "
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "code",
 24 |    "execution_count": 3,
 25 |    "metadata": {},
 26 |    "outputs": [
 27 |     {
 28 |      "name": "stderr",
 29 |      "output_type": "stream",
 30 |      "text": [
 31 |       "Using TensorFlow backend.\n",
 32 |       "/Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
 33 |       "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
 34 |       "/Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
 35 |       "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
 36 |       "/Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
 37 |       "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
 38 |       "/Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
 39 |       "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
 40 |       "/Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
 41 |       "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
 42 |       "/Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
 43 |       "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
 44 |      ]
 45 |     }
 46 |    ],
 47 |    "source": [
 48 |     "from pyspark.sql import SparkSession\n",
 49 |     "from pyspark.ml import Pipeline\n",
 50 |     "from pyspark.ml.feature import VectorAssembler\n",
 51 |     "from sparkdl import readImages\n",
 52 |     "import tensorflow as tf\n",
 53 |     "import tensorframes as tfs"
 54 |    ]
 55 |   },
 56 |   {
 57 |    "cell_type": "code",
 58 |    "execution_count": 4,
 59 |    "metadata": {},
 60 |    "outputs": [],
 61 |    "source": [
 62 |     "spark = SparkSession.builder \\\n",
 63 |     "        .appName(\"PySparkCatDogJob\") \\\n",
 64 |     "        .config(\"spark.jars\", \"*.jar\") \\\n",
 65 |     "        .config(\"packages\",\"databricks:spark-deep-learning:1.5.0-spark2.4-s_2.11,databricks:tensorframes:0.6.0-s_2.11\") \\\n",
 66 |     "        .getOrCreate()\n",
 67 |     "\n",
 68 |     "sc = spark.sparkContext\n",
 69 |     "sc.PACKAGE_EXTENSIONS=(\"databricks:spark-deep-learning:1.5.0-spark2.4-s_2.11,databricks:tensorframes:0.6.0-s_2.11\")"
 70 |    ]
 71 |   },
 72 |   {
 73 |    "cell_type": "code",
 74 |    "execution_count": 5,
 75 |    "metadata": {},
 76 |    "outputs": [
 77 |     {
 78 |      "data": {
 79 |       "text/html": [
 80 |        "\n",
 81 |        "            <div>\n",
 82 |        "                <p><b>SparkSession - in-memory</b></p>\n",
 83 |        "                \n",
 84 |        "        <div>\n",
 85 |        "            <p><b>SparkContext</b></p>\n",
 86 |        "\n",
 87 |        "            <p><a href=\"http://192.168.1.147:4040\">Spark UI</a></p>\n",
 88 |        "\n",
 89 |        "            <dl>\n",
 90 |        "              <dt>Version</dt>\n",
 91 |        "                <dd><code>v2.4.4</code></dd>\n",
 92 |        "              <dt>Master</dt>\n",
 93 |        "                <dd><code>local[*]</code></dd>\n",
 94 |        "              <dt>AppName</dt>\n",
 95 |        "                <dd><code>PySparkCatDogJob</code></dd>\n",
 96 |        "            </dl>\n",
 97 |        "        </div>\n",
 98 |        "        \n",
 99 |        "            </div>\n",
100 |        "        "
101 |       ],
102 |       "text/plain": [
103 |        "<pyspark.sql.session.SparkSession at 0x135d8ae90>"
104 |       ]
105 |      },
106 |      "execution_count": 5,
107 |      "metadata": {},
108 |      "output_type": "execute_result"
109 |     }
110 |    ],
111 |    "source": [
112 |     "spark"
113 |    ]
114 |   },
115 |   {
116 |    "cell_type": "code",
117 |    "execution_count": 6,
118 |    "metadata": {},
119 |    "outputs": [],
120 |    "source": [
121 |     "from pyspark.sql.functions import lit"
122 |    ]
123 |   },
124 |   {
125 |    "cell_type": "code",
126 |    "execution_count": 7,
127 |    "metadata": {},
128 |    "outputs": [],
129 |    "source": [
130 |     "cat_df = readImages(\"cat_dog/cat\").withColumn(\"label\", lit(0))"
131 |    ]
132 |   },
133 |   {
134 |    "cell_type": "code",
135 |    "execution_count": 8,
136 |    "metadata": {},
137 |    "outputs": [],
138 |    "source": [
139 |     "dog_df = readImages(\"cat_dog/dog\").withColumn(\"label\", lit(1))"
140 |    ]
141 |   },
142 |   {
143 |    "cell_type": "code",
144 |    "execution_count": 9,
145 |    "metadata": {},
146 |    "outputs": [
147 |     {
148 |      "name": "stdout",
149 |      "output_type": "stream",
150 |      "text": [
151 |       "root\n",
152 |       " |-- filePath: string (nullable = false)\n",
153 |       " |-- image: struct (nullable = true)\n",
154 |       " |    |-- mode: string (nullable = false)\n",
155 |       " |    |-- height: integer (nullable = false)\n",
156 |       " |    |-- width: integer (nullable = false)\n",
157 |       " |    |-- nChannels: integer (nullable = false)\n",
158 |       " |    |-- data: binary (nullable = false)\n",
159 |       " |-- label: integer (nullable = false)\n",
160 |       "\n"
161 |      ]
162 |     }
163 |    ],
164 |    "source": [
165 |     "cat_df.printSchema()"
166 |    ]
167 |   },
168 |   {
169 |    "cell_type": "code",
170 |    "execution_count": 10,
171 |    "metadata": {},
172 |    "outputs": [],
173 |    "source": [
174 |     "(cat_df_train, cat_df_test) = cat_df.randomSplit([0.7, 0.3])\n",
175 |     "(dog_df_train, dog_df_test) = dog_df.randomSplit([0.7, 0.3])"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "code",
180 |    "execution_count": 11,
181 |    "metadata": {},
182 |    "outputs": [],
183 |    "source": [
184 |     "df_train = cat_df_train.union(dog_df_train)"
185 |    ]
186 |   },
187 |   {
188 |    "cell_type": "code",
189 |    "execution_count": 12,
190 |    "metadata": {},
191 |    "outputs": [],
192 |    "source": [
193 |     "df_test = cat_df_test.union(dog_df_test)"
194 |    ]
195 |   },
196 |   {
197 |    "cell_type": "code",
198 |    "execution_count": 16,
199 |    "metadata": {},
200 |    "outputs": [
201 |     {
202 |      "data": {
203 |       "text/plain": [
204 |        "216"
205 |       ]
206 |      },
207 |      "execution_count": 16,
208 |      "metadata": {},
209 |      "output_type": "execute_result"
210 |     }
211 |    ],
212 |    "source": [
213 |     "df_train.count()"
214 |    ]
215 |   },
216 |   {
217 |    "cell_type": "code",
218 |    "execution_count": 17,
219 |    "metadata": {},
220 |    "outputs": [
221 |     {
222 |      "data": {
223 |       "text/plain": [
224 |        "84"
225 |       ]
226 |      },
227 |      "execution_count": 17,
228 |      "metadata": {},
229 |      "output_type": "execute_result"
230 |     }
231 |    ],
232 |    "source": [
233 |     "df_test.count()"
234 |    ]
235 |   },
236 |   {
237 |    "cell_type": "code",
238 |    "execution_count": 15,
239 |    "metadata": {},
240 |    "outputs": [
241 |     {
242 |      "name": "stdout",
243 |      "output_type": "stream",
244 |      "text": [
245 |       "WARNING:tensorflow:From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py:435: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
246 |       "Instructions for updating:\n",
247 |       "Colocations handled automatically by placer.\n"
248 |      ]
249 |     },
250 |     {
251 |      "name": "stderr",
252 |      "output_type": "stream",
253 |      "text": [
254 |       "2019-12-09 22:53:22,898 WARNING (MainThread-99959) From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py:435: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
255 |       "Instructions for updating:\n",
256 |       "Colocations handled automatically by placer.\n"
257 |      ]
258 |     },
259 |     {
260 |      "name": "stdout",
261 |      "output_type": "stream",
262 |      "text": [
263 |       "WARNING:tensorflow:From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/sparkdl/graph/utils.py:189: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.\n",
264 |       "Instructions for updating:\n",
265 |       "Use tf.compat.v1.graph_util.convert_variables_to_constants\n"
266 |      ]
267 |     },
268 |     {
269 |      "name": "stderr",
270 |      "output_type": "stream",
271 |      "text": [
272 |       "2019-12-09 22:53:31,085 WARNING (MainThread-99959) From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/sparkdl/graph/utils.py:189: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.\n",
273 |       "Instructions for updating:\n",
274 |       "Use tf.compat.v1.graph_util.convert_variables_to_constants\n"
275 |      ]
276 |     },
277 |     {
278 |      "name": "stdout",
279 |      "output_type": "stream",
280 |      "text": [
281 |       "WARNING:tensorflow:From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/graph_util_impl.py:245: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.\n",
282 |       "Instructions for updating:\n",
283 |       "Use tf.compat.v1.graph_util.extract_sub_graph\n"
284 |      ]
285 |     },
286 |     {
287 |      "name": "stderr",
288 |      "output_type": "stream",
289 |      "text": [
290 |       "2019-12-09 22:53:31,086 WARNING (MainThread-99959) From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/tensorflow/python/framework/graph_util_impl.py:245: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.\n",
291 |       "Instructions for updating:\n",
292 |       "Use tf.compat.v1.graph_util.extract_sub_graph\n"
293 |      ]
294 |     },
295 |     {
296 |      "name": "stdout",
297 |      "output_type": "stream",
298 |      "text": [
299 |       "INFO:tensorflow:Froze 376 variables.\n"
300 |      ]
301 |     },
302 |     {
303 |      "name": "stderr",
304 |      "output_type": "stream",
305 |      "text": [
306 |       "2019-12-09 22:53:31,582 INFO (MainThread-99959) Froze 376 variables.\n"
307 |      ]
308 |     },
309 |     {
310 |      "name": "stdout",
311 |      "output_type": "stream",
312 |      "text": [
313 |       "INFO:tensorflow:Converted 376 variables to const ops.\n"
314 |      ]
315 |     },
316 |     {
317 |      "name": "stderr",
318 |      "output_type": "stream",
319 |      "text": [
320 |       "2019-12-09 22:53:31,780 INFO (MainThread-99959) Converted 376 variables to const ops.\n"
321 |      ]
322 |     },
323 |     {
324 |      "name": "stdout",
325 |      "output_type": "stream",
326 |      "text": [
327 |       "WARNING:tensorflow:From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/sparkdl/transformers/tf_image.py:178: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
328 |       "Instructions for updating:\n",
329 |       "Use tf.cast instead.\n"
330 |      ]
331 |     },
332 |     {
333 |      "name": "stderr",
334 |      "output_type": "stream",
335 |      "text": [
336 |       "2019-12-09 22:53:49,286 WARNING (MainThread-99959) From /Users/aleksandrsavchenko/opt/anaconda3/envs/stepik-ds-course/lib/python3.7/site-packages/sparkdl/transformers/tf_image.py:178: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
337 |       "Instructions for updating:\n",
338 |       "Use tf.cast instead.\n"
339 |      ]
340 |     },
341 |     {
342 |      "name": "stdout",
343 |      "output_type": "stream",
344 |      "text": [
345 |       "INFO:tensorflow:Froze 0 variables.\n"
346 |      ]
347 |     },
348 |     {
349 |      "name": "stderr",
350 |      "output_type": "stream",
351 |      "text": [
352 |       "2019-12-09 22:53:50,284 INFO (MainThread-99959) Froze 0 variables.\n"
353 |      ]
354 |     },
355 |     {
356 |      "name": "stdout",
357 |      "output_type": "stream",
358 |      "text": [
359 |       "INFO:tensorflow:Converted 0 variables to const ops.\n"
360 |      ]
361 |     },
362 |     {
363 |      "name": "stderr",
364 |      "output_type": "stream",
365 |      "text": [
366 |       "2019-12-09 22:53:50,401 INFO (MainThread-99959) Converted 0 variables to const ops.\n",
367 |       "2019-12-09 22:53:50,983 INFO (MainThread-99959) Fetch names: ['sdl_flattened_mixed10/concat:0']\n",
368 |       "2019-12-09 22:53:50,984 INFO (MainThread-99959) Spark context = <SparkContext master=local[*] appName=PySparkCatDogJob>\n"
369 |      ]
370 |     }
371 |    ],
372 |    "source": [
373 |     "from pyspark.ml.classification import LogisticRegression\n",
374 |     "from pyspark.ml import Pipeline\n",
375 |     "from sparkdl import DeepImageFeaturizer\n",
376 |     "featurizer = DeepImageFeaturizer(inputCol=\"image\", outputCol=\"features\", modelName=\"InceptionV3\")\n",
377 |     "lr = LogisticRegression(maxIter=1, regParam=0.05, elasticNetParam=0.3, labelCol=\"label\")\n",
378 |     "p = Pipeline(stages=[featurizer, lr]) \n",
379 |     "p_model = p.fit(df_train)"
380 |    ]
381 |   },
382 |   {
383 |    "cell_type": "code",
384 |    "execution_count": 18,
385 |    "metadata": {},
386 |    "outputs": [
387 |     {
388 |      "name": "stdout",
389 |      "output_type": "stream",
390 |      "text": [
391 |       "Test set accuracy = 0.78756454354\n"
392 |      ]
393 |     }
394 |    ],
395 |    "source": [
396 |     "from pyspark.ml.evaluation import MulticlassClassificationEvaluator \n",
397 |     "tested_df = p_model.transform(df_test)\n",
398 |     "evaluator = MulticlassClassificationEvaluator(metricName=\"accuracy\") \n",
399 |     "print(\"Test set accuracy = \" + str(evaluator.evaluate(tested_df.select(\"prediction\", \"label\"))))"
400 |    ]
401 |   },
402 |   {
403 |    "cell_type": "code",
404 |    "execution_count": 19,
405 |    "metadata": {},
406 |    "outputs": [],
407 |    "source": [
408 |     "spark.stop()"
409 |    ]
410 |   },
411 |   {
412 |    "cell_type": "code",
413 |    "execution_count": null,
414 |    "metadata": {},
415 |    "outputs": [],
416 |    "source": []
417 |   }
418 |  ],
419 |  "metadata": {
420 |   "kernelspec": {
421 |    "display_name": "Python 3",
422 |    "language": "python",
423 |    "name": "python3"
424 |   },
425 |   "language_info": {
426 |    "codemirror_mode": {
427 |     "name": "ipython",
428 |     "version": 3
429 |    },
430 |    "file_extension": ".py",
431 |    "mimetype": "text/x-python",
432 |    "name": "python",
433 |    "nbconvert_exporter": "python",
434 |    "pygments_lexer": "ipython3",
435 |    "version": "3.7.5"
436 |   }
437 |  },
438 |  "nbformat": 4,
439 |  "nbformat_minor": 2
440 | }
441 | 


--------------------------------------------------------------------------------
/Week5/SparkML/spark-practice/cat_dog/cat_dog.zip:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/spark-practice/cat_dog/cat_dog.zip


--------------------------------------------------------------------------------
/Week5/SparkML/spark-practice/cat_dog/scala-logging_2.11-3.9.2.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/spark-practice/cat_dog/scala-logging_2.11-3.9.2.jar


--------------------------------------------------------------------------------
/Week5/SparkML/spark-practice/cat_dog/tensorframes-0.6.0-s_2.11.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/spark-practice/cat_dog/tensorframes-0.6.0-s_2.11.jar


--------------------------------------------------------------------------------
/Week5/SparkML/spark-tasks/SparkMLTemplate.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "from pyspark.sql import SparkSession\n",
 10 |     "from pyspark.ml import Pipeline\n",
 11 |     "from pyspark.sql.functions import mean,col,split, col, regexp_extract, when, lit\n",
 12 |     "from pyspark.ml.feature import StringIndexer\n",
 13 |     "from pyspark.ml.feature import VectorAssembler\n",
 14 |     "from pyspark.ml.evaluation import MulticlassClassificationEvaluator\n",
 15 |     "from pyspark.ml.feature import QuantileDiscretizer\n",
 16 |     "from pyspark.ml.classification import LogisticRegression\n",
 17 |     "from pyspark.ml.classification import DecisionTreeClassifier\n",
 18 |     "from pyspark.ml.classification import RandomForestClassifier\n",
 19 |     "from pyspark.ml.classification import GBTClassifier\n",
 20 |     "from pyspark.ml.clustering import KMeans\n",
 21 |     "from pyspark.ml.evaluation import ClusteringEvaluator\n",
 22 |     "from pyspark.ml.regression import LinearRegression"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": null,
 28 |    "metadata": {},
 29 |    "outputs": [],
 30 |    "source": [
 31 |     "import random\n",
 32 |     "import numpy as np\n",
 33 |     "#set seed\n",
 34 |     "random.seed(1234)\n",
 35 |     "np.random.seed(1234)"
 36 |    ]
 37 |   },
 38 |   {
 39 |    "cell_type": "code",
 40 |    "execution_count": null,
 41 |    "metadata": {},
 42 |    "outputs": [],
 43 |    "source": [
 44 |     "spark = SparkSession.builder.appName(\"PySparkML\").getOrCreate()"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "code",
 49 |    "execution_count": null,
 50 |    "metadata": {},
 51 |    "outputs": [],
 52 |    "source": [
 53 |     "spark"
 54 |    ]
 55 |   },
 56 |   {
 57 |    "cell_type": "markdown",
 58 |    "metadata": {},
 59 |    "source": [
 60 |     "## №1 Линейная регрессия"
 61 |    ]
 62 |   },
 63 |   {
 64 |    "cell_type": "markdown",
 65 |    "metadata": {},
 66 |    "source": [
 67 |     "Загрузите данные для применения линейной регрессии <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week5/SparkML/spark-tasks/linear_regression.parquet\">linear_regression.parquet</a>"
 68 |    ]
 69 |   },
 70 |   {
 71 |    "cell_type": "code",
 72 |    "execution_count": null,
 73 |    "metadata": {},
 74 |    "outputs": [],
 75 |    "source": [
 76 |     "lr_df = #Ваш код"
 77 |    ]
 78 |   },
 79 |   {
 80 |    "cell_type": "code",
 81 |    "execution_count": null,
 82 |    "metadata": {},
 83 |    "outputs": [],
 84 |    "source": [
 85 |     "lr_df.show(5)"
 86 |    ]
 87 |   },
 88 |   {
 89 |    "cell_type": "markdown",
 90 |    "metadata": {},
 91 |    "source": [
 92 |     "Создайте учителя линейной регресии со следующими параметрами:\n",
 93 |     "maxIter=20\n",
 94 |     "regParam=0.5\n",
 95 |     "elasticNetParam=0.75<br>\n",
 96 |     "<a href=\"https://spark.apache.org/docs/latest/ml-classification-regression.html#linear-regression\">LinearRegression</a>"
 97 |    ]
 98 |   },
 99 |   {
100 |    "cell_type": "code",
101 |    "execution_count": null,
102 |    "metadata": {},
103 |    "outputs": [],
104 |    "source": [
105 |     "lr = #Ваш код"
106 |    ]
107 |   },
108 |   {
109 |    "cell_type": "markdown",
110 |    "metadata": {},
111 |    "source": [
112 |     "Выполните обучения на загруженных данных и сохраните результат в переменную."
113 |    ]
114 |   },
115 |   {
116 |    "cell_type": "code",
117 |    "execution_count": null,
118 |    "metadata": {},
119 |    "outputs": [],
120 |    "source": [
121 |     "lrModel = #Ваш код"
122 |    ]
123 |   },
124 |   {
125 |    "cell_type": "markdown",
126 |    "metadata": {},
127 |    "source": [
128 |     "Найдите следующие параметры полученной модели rootMeanSquaredError (RMSE), r2 и округлити их до 3его знака."
129 |    ]
130 |   },
131 |   {
132 |    "cell_type": "code",
133 |    "execution_count": null,
134 |    "metadata": {},
135 |    "outputs": [],
136 |    "source": [
137 |     "#Ваш код"
138 |    ]
139 |   },
140 |   {
141 |    "cell_type": "markdown",
142 |    "metadata": {},
143 |    "source": [
144 |     "## №2 Кластеризация (K-Means)"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "markdown",
149 |    "metadata": {},
150 |    "source": [
151 |     "Загрузите данные для применения из <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week5/SparkML/spark-tasks/wine.parquet\">wine.parquet</a>"
152 |    ]
153 |   },
154 |   {
155 |    "cell_type": "code",
156 |    "execution_count": null,
157 |    "metadata": {},
158 |    "outputs": [],
159 |    "source": [
160 |     "wine_df = #Ваш код"
161 |    ]
162 |   },
163 |   {
164 |    "cell_type": "code",
165 |    "execution_count": null,
166 |    "metadata": {},
167 |    "outputs": [],
168 |    "source": [
169 |     "wine_df.show(5)"
170 |    ]
171 |   },
172 |   {
173 |    "cell_type": "markdown",
174 |    "metadata": {},
175 |    "source": [
176 |     "Примените <a href=\"https://spark.apache.org/docs/latest/ml-features.html#vectorassembler\">VectorAssembler</a> для создания вектора фич (задействуйте все свойства, кроме Customer_Segment)."
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "code",
181 |    "execution_count": null,
182 |    "metadata": {},
183 |    "outputs": [],
184 |    "source": [
185 |     "feature = #Ваш код"
186 |    ]
187 |   },
188 |   {
189 |    "cell_type": "markdown",
190 |    "metadata": {},
191 |    "source": [
192 |     "Cоздайте учителя KMeans со следующими параметрами K=3 Seed=1<br>\n",
193 |     "Обучите модель и примените ее к тому же вектору.\n",
194 |     "Документация по <a href=\"https://spark.apache.org/docs/latest/ml-clustering.html#k-means\">KMeans</a>"
195 |    ]
196 |   },
197 |   {
198 |    "cell_type": "code",
199 |    "execution_count": null,
200 |    "metadata": {},
201 |    "outputs": [],
202 |    "source": [
203 |     "#Ваш код"
204 |    ]
205 |   },
206 |   {
207 |    "cell_type": "markdown",
208 |    "metadata": {},
209 |    "source": [
210 |     "Найдите силуэт с евклидовым расстоянием в квадрате для данных по вину(округлите до четвертого знака).\n",
211 |     "<br><a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.ml.html#pyspark.ml.evaluation.ClusteringEvaluator\">ClusteringEvaluator</a>"
212 |    ]
213 |   },
214 |   {
215 |    "cell_type": "code",
216 |    "execution_count": null,
217 |    "metadata": {},
218 |    "outputs": [],
219 |    "source": [
220 |     "#Ваш код"
221 |    ]
222 |   },
223 |   {
224 |    "cell_type": "markdown",
225 |    "metadata": {},
226 |    "source": [
227 |     "## №3 DecisionTreeClassifier"
228 |    ]
229 |   },
230 |   {
231 |    "cell_type": "markdown",
232 |    "metadata": {},
233 |    "source": [
234 |     "Загрузити датасет из файла <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week5/SparkML/spark-tasks/iris.parquet\">iris.parquet</a>"
235 |    ]
236 |   },
237 |   {
238 |    "cell_type": "code",
239 |    "execution_count": null,
240 |    "metadata": {},
241 |    "outputs": [],
242 |    "source": [
243 |     "iris_df = #Ваш код"
244 |    ]
245 |   },
246 |   {
247 |    "cell_type": "code",
248 |    "execution_count": null,
249 |    "metadata": {},
250 |    "outputs": [],
251 |    "source": [
252 |     "iris_df.show(5)"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "markdown",
257 |    "metadata": {},
258 |    "source": [
259 |     "Составьте из наших признаков вектор применив <a href=\"https://spark.apache.org/docs/latest/ml-features.html#vectorassembler\">VectorAssembler</a> как колонку features.\n",
260 |     "<br> Задействуйте все признаки, кроме species, так как он является целевым."
261 |    ]
262 |   },
263 |   {
264 |    "cell_type": "code",
265 |    "execution_count": null,
266 |    "metadata": {},
267 |    "outputs": [],
268 |    "source": [
269 |     "#Ваш код"
270 |    ]
271 |   },
272 |   {
273 |    "cell_type": "markdown",
274 |    "metadata": {},
275 |    "source": [
276 |     "Используйте <a href=\"https://spark.apache.org/docs/latest/ml-features.html#stringindexer\">StringIndexer</a> и сделайте новый признак с именем type из целевого признака species который является категориальным."
277 |    ]
278 |   },
279 |   {
280 |    "cell_type": "code",
281 |    "execution_count": null,
282 |    "metadata": {},
283 |    "outputs": [],
284 |    "source": [
285 |     "#Ваш код"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": null,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "iris_df.show(5)"
295 |    ]
296 |   },
297 |   {
298 |    "cell_type": "markdown",
299 |    "metadata": {},
300 |    "source": [
301 |     "Сформируем выборки на обучение и тест."
302 |    ]
303 |   },
304 |   {
305 |    "cell_type": "code",
306 |    "execution_count": null,
307 |    "metadata": {},
308 |    "outputs": [],
309 |    "source": [
310 |     "(training_data, test_data) = iris_df.randomSplit([0.8, 0.2],seed = 42)"
311 |    ]
312 |   },
313 |   {
314 |    "cell_type": "markdown",
315 |    "metadata": {},
316 |    "source": [
317 |     "Создайте и обучите <a href=\"https://spark.apache.org/docs/latest/ml-classification-regression.html#decision-tree-classifier\">DecisionTreeClassifier</a> на датасете для обучения.\n",
318 |     "Полученную модель используйте над тестовым датасетом."
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": null,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "from pyspark.ml.classification import DecisionTreeClassifier\n",
328 |     "#Ваш код"
329 |    ]
330 |   },
331 |   {
332 |    "cell_type": "markdown",
333 |    "metadata": {},
334 |    "source": [
335 |     "Используйте <a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.ml.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator\">MulticlassClassificationEvaluator</a> (помните что целевая фича это - type) для оценки качества модели по метрике accuracy.<br>Какая точность полученной модели?"
336 |    ]
337 |   },
338 |   {
339 |    "cell_type": "code",
340 |    "execution_count": null,
341 |    "metadata": {},
342 |    "outputs": [],
343 |    "source": [
344 |     "#Ваш код"
345 |    ]
346 |   },
347 |   {
348 |    "cell_type": "markdown",
349 |    "metadata": {},
350 |    "source": [
351 |     "## №4 Random forest"
352 |    ]
353 |   },
354 |   {
355 |    "cell_type": "markdown",
356 |    "metadata": {},
357 |    "source": [
358 |     "Создайте и обучите <a href=\"https://spark.apache.org/docs/latest/ml-classification-regression.html#random-forest-classifier\">RandomForestClassifier</a> из 10 деревьев на датасете для обучения.\n",
359 |     "Полученную модель примените к тестовому датасету.\n"
360 |    ]
361 |   },
362 |   {
363 |    "cell_type": "code",
364 |    "execution_count": null,
365 |    "metadata": {},
366 |    "outputs": [],
367 |    "source": [
368 |     "from pyspark.ml.classification import RandomForestClassifier\n",
369 |     "#Ваш код"
370 |    ]
371 |   },
372 |   {
373 |    "cell_type": "markdown",
374 |    "metadata": {},
375 |    "source": [
376 |     "Используйте <a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.ml.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator\">MulticlassClassificationEvaluator</a> (помните что целевая фича это - type) для оценки качества модели по метрике accuracy.<br>Какая точность полученной модели?"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": null,
382 |    "metadata": {},
383 |    "outputs": [],
384 |    "source": [
385 |     "#Ваш код"
386 |    ]
387 |   },
388 |   {
389 |    "cell_type": "markdown",
390 |    "metadata": {},
391 |    "source": [
392 |     "## №5 Hyperparameter tuning"
393 |    ]
394 |   },
395 |   {
396 |    "cell_type": "markdown",
397 |    "metadata": {},
398 |    "source": [
399 |     "Займемся оптимизацией гиперпараметров для модели.\n",
400 |     "Примените <a href='https://spark.apache.org/docs/latest/ml-tuning.html#train-validation-split'>TrainValidationSplit</a> для оптимизации гиперпараметров используя подготовленный вами выше датасет <a href=\"https://github.com/AlexKbit/stepik-ds-course/raw/master/Week5/SparkML/spark-tasks/iris.parquet\">iris.parquet</a> на модели <a href=\"https://spark.apache.org/docs/latest/ml-classification-regression.html#random-forest-classifier\">RandomForestClassifier</a> совместно с <a href=\"https://spark.apache.org/docs/latest/api/python/pyspark.ml.html#pyspark.ml.evaluation.MulticlassClassificationEvaluator\">MulticlassClassificationEvaluator</a>.\n",
401 |     "<br>Ваша цель определить оптимальные значения параметров из следующих диапазонов:\n",
402 |     "<br>impurity = [\"entropy\", \"gini\"]\n",
403 |     "<br>maxDepth = [2, 3, 4, 5]\n",
404 |     "<br>numTrees = [3, 6, 9, 12, 15, 18, 21]"
405 |    ]
406 |   },
407 |   {
408 |    "cell_type": "code",
409 |    "execution_count": null,
410 |    "metadata": {},
411 |    "outputs": [],
412 |    "source": [
413 |     "from pyspark.ml.tuning import ParamGridBuilder, TrainValidationSplit"
414 |    ]
415 |   },
416 |   {
417 |    "cell_type": "code",
418 |    "execution_count": null,
419 |    "metadata": {},
420 |    "outputs": [],
421 |    "source": [
422 |     "model = #Ваш код"
423 |    ]
424 |   },
425 |   {
426 |    "cell_type": "code",
427 |    "execution_count": null,
428 |    "metadata": {},
429 |    "outputs": [],
430 |    "source": [
431 |     "print('Num Trees: {}'.format(model.bestModel._java_obj.getNumTrees()))\n",
432 |     "print('Max Depth: {}'.format(model.bestModel._java_obj.getMaxDepth()))\n",
433 |     "print('Impurity: {}'.format(model.bestModel._java_obj.getImpurity()))"
434 |    ]
435 |   }
436 |  ],
437 |  "metadata": {
438 |   "kernelspec": {
439 |    "display_name": "Python 3",
440 |    "language": "python",
441 |    "name": "python3"
442 |   },
443 |   "language_info": {
444 |    "codemirror_mode": {
445 |     "name": "ipython",
446 |     "version": 3
447 |    },
448 |    "file_extension": ".py",
449 |    "mimetype": "text/x-python",
450 |    "name": "python",
451 |    "nbconvert_exporter": "python",
452 |    "pygments_lexer": "ipython3",
453 |    "version": "3.7.4"
454 |   }
455 |  },
456 |  "nbformat": 4,
457 |  "nbformat_minor": 2
458 | }
459 | 


--------------------------------------------------------------------------------
/Week5/SparkML/spark-tasks/iris.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/spark-tasks/iris.parquet


--------------------------------------------------------------------------------
/Week5/SparkML/spark-tasks/linear_regression.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/spark-tasks/linear_regression.parquet


--------------------------------------------------------------------------------
/Week5/SparkML/spark-tasks/wine.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/Week5/SparkML/spark-tasks/wine.parquet


--------------------------------------------------------------------------------
/Week5/help.txt:
--------------------------------------------------------------------------------
1 | Для работы необходимы:
2 | 1) Python 3.X+
3 | 2) Jupyter Notebook
4 | 3) PySpark
5 | pip install pyspark


--------------------------------------------------------------------------------
/Week6/Superset/.env:
--------------------------------------------------------------------------------
 1 | # metadata database environment variables.
 2 | MYSQL_USER=superset
 3 | MYSQL_PASSWORD=superset
 4 | MYSQL_DATABASE=superset
 5 | MYSQL_ROOT_PASSWORD=root
 6 | 
 7 | # redis environment variables.
 8 | REDIS_HOST=redis
 9 | REDIS_PORT=6379
10 | 
11 | # superset environment variables.
12 | MYSQL_HOST=mysql
13 | MYSQL_PORT=3306
14 | SUPERSET_ENV=local
15 | SUPERSET_VERSION=0.29.0rc5
16 | 


--------------------------------------------------------------------------------
/Week6/Superset/config/superset_config.py:
--------------------------------------------------------------------------------
 1 | import os
 2 | from superset.config import *
 3 | from werkzeug.contrib.cache import RedisCache
 4 | 
 5 | 
 6 | def get_env_variable(var_name, default=None):
 7 |     """Get the environment variable or raise exception."""
 8 |     try:
 9 |         return os.environ[var_name]
10 |     except KeyError:
11 |         if default is not None:
12 |             return default
13 |         else:
14 |             error_msg = 'The environment variable {} was missing, abort...' \
15 |                 .format(var_name)
16 |             raise EnvironmentError(error_msg)
17 | 
18 | invocation_type = get_env_variable('INVOCATION_TYPE')
19 | if invocation_type == 'COMPOSE':
20 |     MYSQL_USER = get_env_variable('MYSQL_USER')
21 |     MYSQL_PASS = get_env_variable('MYSQL_PASS')
22 |     MYSQL_HOST = get_env_variable('MYSQL_HOST')
23 |     MYSQL_PORT = get_env_variable('MYSQL_PORT')
24 |     MYSQL_DATABASE = get_env_variable('MYSQL_DATABASE')
25 | 
26 |     # The SQLAlchemy connection string.
27 |     SQLALCHEMY_DATABASE_URI = 'mysql://%s:%s@%s:%s/%s' % (MYSQL_USER,
28 |                                                           MYSQL_PASS,
29 |                                                           MYSQL_HOST,
30 |                                                           MYSQL_PORT,
31 |                                                           MYSQL_DATABASE)
32 | elif invocation_type == 'RUN':
33 |     SQLALCHEMY_DATABASE_URI = get_env_variable('DB_URL')
34 | else:
35 |     SQLALCHEMY_DATABASE_URI = 'sqlite:///' + os.path.join(DATA_DIR, 'superset.db')
36 | 
37 | REDIS_HOST=''
38 | REDIS_PORT=''
39 | if invocation_type == 'COMPOSE':
40 |     REDIS_HOST = get_env_variable('REDIS_HOST')
41 |     REDIS_PORT = get_env_variable('REDIS_PORT')
42 |     RESULTS_BACKEND = RedisCache(host=REDIS_HOST, port=REDIS_PORT, key_prefix='superset_results')
43 | elif invocation_type == 'RUN':
44 |     REDIS_HOST = get_env_variable('REDIS_URL').split(":")[1].replace("/","")
45 |     REDIS_PORT = get_env_variable('REDIS_URL').split(":")[2].replace("/0","")
46 |     RESULTS_BACKEND = RedisCache(host=REDIS_HOST, port=REDIS_PORT, key_prefix='superset_results')
47 | else:
48 |     RESULTS_BACKEND = None
49 | 
50 | class CeleryConfig(object):
51 |     BROKER_URL = ('redis://%s:%s/0' % (REDIS_HOST, REDIS_PORT), 'sqla+sqlite:///'+ os.path.join(DATA_DIR, 'celeryDB.db'))[bool(not REDIS_HOST)]
52 |     CELERY_RESULT_BACKEND = ('redis://%s:%s/0' % (REDIS_HOST, REDIS_PORT), 'db+sqlite:///'+ os.path.join(DATA_DIR, 'celeryResultDB.db'))[bool(not REDIS_HOST)]
53 |     CELERY_ANNOTATIONS = {'tasks.add': {'rate_limit': '10/s'}}
54 |     CELERY_IMPORTS = ('superset.sql_lab', )
55 |     CELERY_TASK_PROTOCOL = 1
56 | 
57 | 
58 | CELERY_CONFIG = CeleryConfig
59 | 


--------------------------------------------------------------------------------
/Week6/Superset/docker-compose.yaml:
--------------------------------------------------------------------------------
 1 | version: '3'
 2 | services:
 3 |   redis:
 4 |     image: redis:3.2
 5 |     restart: always
 6 |     ports:
 7 |       - 6379:6379
 8 |     volumes:
 9 |       - redis:/data
10 |   mysql:
11 |     image: mysql:5.7
12 |     restart: always
13 |     environment:
14 |       MYSQL_USER: ${MYSQL_USER}
15 |       MYSQL_PASSWORD: ${MYSQL_PASSWORD}
16 |       MYSQL_DATABASE: ${MYSQL_DATABASE}
17 |       MYSQL_ROOT_PASSWORD: ${MYSQL_ROOT_PASSWORD}
18 |     ports:
19 |       - 3306:3306
20 |     volumes:
21 |       - mysql:/var/lib/mysql
22 |   superset:
23 |     image: abhioncbr/docker-superset:${SUPERSET_VERSION}
24 |     restart: always
25 |     environment:
26 |       ADMIN_USERNAME: admin
27 |       ADMIN_PWD: superset
28 |       MYSQL_USER: ${MYSQL_USER}
29 |       MYSQL_PASS: ${MYSQL_PASSWORD}
30 |       MYSQL_DATABASE: ${MYSQL_DATABASE}
31 |       MYSQL_HOST: ${MYSQL_HOST}
32 |       MYSQL_PORT: ${MYSQL_PORT}
33 |       REDIS_HOST: ${REDIS_HOST}
34 |       REDIS_PORT: ${REDIS_PORT}
35 |       SUPERSET_ENV: ${SUPERSET_ENV}
36 |     user: root:root
37 |     ports:
38 |       - 8088:8088
39 |       - 5555:5555
40 |     depends_on:
41 |       - mysql
42 |       - redis
43 |     volumes:
44 |       - ../config/:/home/superset/config/
45 | volumes:
46 |   mysql:
47 |     external: false
48 |   redis:
49 |     external: false
50 | 


--------------------------------------------------------------------------------
/Week6/help.txt:
--------------------------------------------------------------------------------
 1 | Выполнять из папки Week6/Superset
 2 | 1) Запуск контейнеров
 3 |     docker-compose up -d
 4 | 2) Проверка запущенных контейнеров
 5 |     docker ps
 6 | 3) Web UI: http://localhost:8088
 7 |     login: admin
 8 |     password: admin
 9 | 4) Работа с Superset
10 |     ...
11 | 5) Остановка контейнеров
12 |     docker-compose down


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/CAP-Theorem.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/workshops/1. DB_Hadoop/CAP-Theorem.png


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/docker-compose.yml:
--------------------------------------------------------------------------------
 1 | version: "3"
 2 | 
 3 | services:
 4 |   namenode:
 5 |     image: bde2020/hadoop-namenode:2.0.0-hadoop3.2.1-java8
 6 |     container_name: namenode
 7 |     restart: always
 8 |     ports:
 9 |       - 9870:9870
10 |       - 9000:9000
11 |     volumes:
12 |       - hadoop_namenode:/hadoop/dfs/name
13 |       - ./tmp/data:/course/data
14 |       - ./tmp/input:/course/input
15 |       - ./tmp/job:/job
16 |       - ./tmp/init:/init
17 |     #command: sh /init/init.sh
18 |     environment:
19 |       - CLUSTER_NAME=test
20 |     env_file:
21 |       - ./hadoop.env
22 | 
23 |   datanode:
24 |     image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
25 |     container_name: datanode
26 |     restart: always
27 |     volumes:
28 |       - hadoop_datanode:/hadoop/dfs/data
29 |     environment:
30 |       SERVICE_PRECONDITION: "namenode:9870"
31 |     env_file:
32 |       - ./hadoop.env
33 | 
34 |   datanode2:
35 |     image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
36 |     container_name: datanode2
37 |     restart: always
38 |     volumes:
39 |       - hadoop_datanode2:/hadoop/dfs/data
40 |     environment:
41 |       SERVICE_PRECONDITION: "namenode:9870"
42 |     env_file:
43 |       - ./hadoop.env
44 | 
45 |   datanode3:
46 |     image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
47 |     container_name: datanode3
48 |     restart: always
49 |     volumes:
50 |       - hadoop_datanode3:/hadoop/dfs/data
51 |     environment:
52 |       SERVICE_PRECONDITION: "namenode:9870"
53 |     env_file:
54 |       - ./hadoop.env
55 | 
56 |   resourcemanager:
57 |     image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.2.1-java8
58 |     container_name: resourcemanager
59 |     restart: always
60 |     ports:
61 |       - 8088:8088
62 |     environment:
63 |       SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864"
64 |     env_file:
65 |       - ./hadoop.env
66 | 
67 |   nodemanager1:
68 |     image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.2.1-java8
69 |     container_name: nodemanager
70 |     restart: always
71 |     environment:
72 |       SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
73 |     env_file:
74 |       - ./hadoop.env
75 | 
76 |   historyserver:
77 |     image: bde2020/hadoop-historyserver:2.0.0-hadoop3.2.1-java8
78 |     container_name: historyserver
79 |     restart: always
80 |     environment:
81 |       SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
82 |     volumes:
83 |       - hadoop_historyserver:/hadoop/yarn/timeline
84 |     env_file:
85 |       - ./hadoop.env
86 | 
87 | volumes:
88 |   hadoop_namenode:
89 |   hadoop_datanode:
90 |   hadoop_datanode2:
91 |   hadoop_datanode3:
92 |   hadoop_historyserver:
93 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/hadoop.env:
--------------------------------------------------------------------------------
 1 | CORE_CONF_fs_defaultFS=hdfs://namenode:9000
 2 | CORE_CONF_hadoop_http_staticuser_user=root
 3 | CORE_CONF_hadoop_proxyuser_hue_hosts=*
 4 | CORE_CONF_hadoop_proxyuser_hue_groups=*
 5 | CORE_CONF_io_compression_codecs=org.apache.hadoop.io.compress.SnappyCodec
 6 | 
 7 | HDFS_CONF_dfs_webhdfs_enabled=true
 8 | HDFS_CONF_dfs_permissions_enabled=false
 9 | HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false
10 | 
11 | YARN_CONF_yarn_log___aggregation___enable=true
12 | YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
13 | YARN_CONF_yarn_resourcemanager_recovery_enabled=true
14 | YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
15 | YARN_CONF_yarn_resourcemanager_scheduler_class=org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler
16 | YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___mb=8192
17 | YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___vcores=4
18 | YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
19 | YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
20 | YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
21 | YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
22 | YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
23 | YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031
24 | YARN_CONF_yarn_timeline___service_enabled=true
25 | YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
26 | YARN_CONF_yarn_timeline___service_hostname=historyserver
27 | YARN_CONF_mapreduce_map_output_compress=true
28 | YARN_CONF_mapred_map_output_compress_codec=org.apache.hadoop.io.compress.SnappyCodec
29 | YARN_CONF_yarn_nodemanager_resource_memory___mb=16384
30 | YARN_CONF_yarn_nodemanager_resource_cpu___vcores=8
31 | YARN_CONF_yarn_nodemanager_disk___health___checker_max___disk___utilization___per___disk___percentage=98.5
32 | YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
33 | YARN_CONF_yarn_nodemanager_aux___services=mapreduce_shuffle
34 | 
35 | MAPRED_CONF_mapreduce_framework_name=yarn
36 | MAPRED_CONF_mapred_child_java_opts=-Xmx4096m
37 | MAPRED_CONF_mapreduce_map_memory_mb=4096
38 | MAPRED_CONF_mapreduce_reduce_memory_mb=8192
39 | MAPRED_CONF_mapreduce_map_java_opts=-Xmx3072m
40 | MAPRED_CONF_mapreduce_reduce_java_opts=-Xmx6144m
41 | MAPRED_CONF_yarn_app_mapreduce_am_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
42 | MAPRED_CONF_mapreduce_map_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
43 | MAPRED_CONF_mapreduce_reduce_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/init4win.bat:
--------------------------------------------------------------------------------
1 | @ECHO OFF
2 | docker cp ./tmp/data namenode:/course/data
3 | docker cp ./tmp/input namenode:/course/input
4 | docker cp ./tmp/job namenode:/job
5 | docker cp ./tmp/init namenode:/init
6 | ECHO All data has been copied successfully.


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/data/checkdata.txt:
--------------------------------------------------------------------------------
1 | Some data
2 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/data/checkdata2.txt:
--------------------------------------------------------------------------------
1 | 0101020201020304038974589381219038190288237520834203482039529874359273648723658743753094589023842093742983759843658734643808203482935839485739464389572037409238420938023975394857394653487230423094820934820385739486538746583457289470239482093842093850394739846794836598347528947092384209384209375938457394865834752837402398402938409235830945739845769384653984752093480298405938450934759836798347534759304597
2 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/data/checkdata3.txt:
--------------------------------------------------------------------------------
1 | 0101020201020304038974589381219038190288237520834203482039529874359273648723658743753094589023842093742983759843658734643808203482935839485739464389572037409238420938023975394857394653487230423094820934820385739486538746583457289470239482093842093850394739846794836598347528947092384209384209375938457394865834752837402398402938409235830945739845769384653984752093480298405938450934759836798347534759304597
2 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/data/checkdata4.txt:
--------------------------------------------------------------------------------
1 | Data4
2 | 
3 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/data/checkdata5.txt:
--------------------------------------------------------------------------------
1 | Data5
2 | 
3 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/init/init.sh:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env bash
2 | hdfs dfs -mkdir /data
3 | hdfs dfs -mkdir /input
4 | hdfs dfs -put /course/data/* /data/
5 | hdfs dfs -put /course/input/* /input/
6 | echo "Initialization complete"


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/docker-hadoop/tmp/input/input.txt:
--------------------------------------------------------------------------------
1 | my data so big my data so big my data so big my data so big
2 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/README.md:
--------------------------------------------------------------------------------
 1 | 
 2 | ## Testing
 3 | Load data into Hive:
 4 | ```
 5 |   docker-compose exec hive-server bash
 6 | 
 7 |   hdfs dfs -mkdir /data
 8 | 
 9 |   hdfs dfs -put /data/users_20210501.csv /data
10 |   hdfs dfs -put /data/users_20210502.csv /data
11 | 
12 |   hive
13 | 
14 |   CREATE EXTERNAL TABLE IF NOT EXISTS users(
15 |           id INT,
16 |           login STRING,
17 |           email STRING,
18 |           active BOOLEAN,
19 |           organization_id INT)
20 |       ROW FORMAT DELIMITED
21 |       FIELDS TERMINATED BY ','
22 |       STORED AS TEXTFILE
23 |       location 'hdfs:///data';
24 | 
25 | ```
26 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/data/create.sql:
--------------------------------------------------------------------------------
 1 | CREATE EXTERNAL TABLE IF NOT EXISTS users(
 2 |         id INT,
 3 |         login STRING,
 4 |         email STRING,
 5 |         active BOOLEAN,
 6 |         organization_id INT)
 7 |     ROW FORMAT DELIMITED
 8 |     FIELDS TERMINATED BY ','
 9 |     STORED AS TEXTFILE
10 |     location 'hdfs:///data';


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/data/init.sh:
--------------------------------------------------------------------------------
1 | hdfs dfs -mkdir /data
2 | hdfs dfs -put /data/users_20210501.csv /data
3 | hdfs dfs -put /data/users_20210502.csv /data
4 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/data/users_20210501.csv:
--------------------------------------------------------------------------------
1 | 1,gregor,gregor@fake.com,true,1001
2 | 2,jess,jess@fake.com,true,1001
3 | 3,pikachu,pikachu@fake.com,true,1001
4 | 4,jerry,jerry@fake.com,false,1001
5 | 5,lolly,lolly@fake.com,false,1001
6 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/data/users_20210502.csv:
--------------------------------------------------------------------------------
1 | 6,stella,stella@fake.com,true,1001
2 | 7,bella,bella@fake.com,true,1001
3 | 8,ingrid,ingrid@fake.com,true,1001
4 | 9,freya,freya@fake.com,true,1001
5 | 10,zik,zik@fake.com,true,1001
6 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/docker-compose.yml:
--------------------------------------------------------------------------------
 1 | version: "3"
 2 | 
 3 | services:
 4 |   namenode:
 5 |     image: bde2020/hadoop-namenode:2.0.0-hadoop2.7.4-java8
 6 |     container_name: namenode
 7 |     ports:
 8 |       - 9870:9870
 9 |       - 9000:9000
10 |       - 50070:50070
11 |     volumes:
12 |       - hadoop_namenode:/hadoop/dfs/name
13 |     environment:
14 |       - CLUSTER_NAME=test
15 |     env_file:
16 |       - ./hadoop.env
17 | 
18 |   datanode:
19 |     image: bde2020/hadoop-datanode:2.0.0-hadoop2.7.4-java8
20 |     container_name: datanode
21 |     ports:
22 |       - 50075:50075
23 |     volumes:
24 |       - hadoop_datanode:/hadoop/dfs/data
25 |     environment:
26 |       SERVICE_PRECONDITION: "namenode:50070"
27 |     env_file:
28 |       - ./hadoop.env
29 | 
30 |   resourcemanager:
31 |     image: bde2020/hadoop-resourcemanager:2.0.0-hadoop2.7.4-java8
32 |     container_name: resourcemanager
33 |     ports:
34 |       - 8088:8088
35 |     environment:
36 |       SERVICE_PRECONDITION: "namenode:50070 datanode:50075"
37 |     env_file:
38 |       - ./hadoop.env
39 | 
40 |   nodemanager:
41 |     image: bde2020/hadoop-nodemanager:2.0.0-hadoop2.7.4-java8
42 |     container_name: nodemanager
43 |     environment:
44 |       SERVICE_PRECONDITION: "namenode:50070 datanode:50075 resourcemanager:8088"
45 |     env_file:
46 |       - ./hadoop.env
47 | 
48 |   historyserver:
49 |     image: bde2020/hadoop-historyserver:2.0.0-hadoop2.7.4-java8
50 |     container_name: historyserver
51 |     environment:
52 |       SERVICE_PRECONDITION: "namenode:50070 datanode:50075 resourcemanager:8088"
53 |     volumes:
54 |       - hadoop_historyserver:/hadoop/yarn/timeline
55 |     env_file:
56 |       - ./hadoop.env
57 | 
58 |   hive-metastore-postgresql:
59 |     image: bde2020/hive-metastore-postgresql:2.3.0
60 |     container_name: hive-metastore-postgresql
61 | 
62 |   hive-server:
63 |     image: bde2020/hive:2.3.2-postgresql-metastore
64 |     container_name: hive-server
65 |     ports:
66 |       - 10000:10000
67 |     volumes:
68 |       - ./data:/data
69 |     environment:
70 |       HIVE_CORE_CONF_javax_jdo_option_ConnectionURL: "jdbc:postgresql://hive-metastore/metastore"
71 |       SERVICE_PRECONDITION: "hive-metastore:9083"
72 |     env_file:
73 |       - ./hadoop.env
74 | 
75 |   hive-metastore:
76 |     image: bde2020/hive:2.3.2-postgresql-metastore
77 |     container_name: hive-metastore
78 |     ports:
79 |       - 9083:9083
80 |     environment:
81 |       SERVICE_PRECONDITION: "namenode:50070 datanode:50075 hive-metastore-postgresql:5432"
82 |     env_file:
83 |       - ./hadoop.env
84 |     command: /opt/hive/bin/hive --service metastore
85 | 
86 | volumes:
87 |   hadoop_namenode:
88 |   hadoop_datanode:
89 |   hadoop_historyserver:
90 | 


--------------------------------------------------------------------------------
/workshops/1. DB_Hadoop/hadoop-with-hive/hadoop.env:
--------------------------------------------------------------------------------
 1 | CORE_CONF_fs_defaultFS=hdfs://namenode:8020
 2 | CORE_CONF_hadoop_http_staticuser_user=root
 3 | CORE_CONF_hadoop_proxyuser_hue_hosts=*
 4 | CORE_CONF_hadoop_proxyuser_hue_groups=*
 5 | CORE_CONF_io_compression_codecs=org.apache.hadoop.io.compress.SnappyCodec
 6 | 
 7 | HDFS_CONF_dfs_webhdfs_enabled=true
 8 | HDFS_CONF_dfs_permissions_enabled=false
 9 | HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false
10 | 
11 | YARN_CONF_yarn_log___aggregation___enable=true
12 | YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
13 | YARN_CONF_yarn_resourcemanager_recovery_enabled=true
14 | YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
15 | YARN_CONF_yarn_resourcemanager_scheduler_class=org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler
16 | YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___mb=8192
17 | YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___vcores=4
18 | YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
19 | YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
20 | YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
21 | YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
22 | YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
23 | YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031
24 | YARN_CONF_yarn_timeline___service_enabled=true
25 | YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
26 | YARN_CONF_yarn_timeline___service_hostname=historyserver
27 | YARN_CONF_mapreduce_map_output_compress=true
28 | YARN_CONF_mapred_map_output_compress_codec=org.apache.hadoop.io.compress.SnappyCodec
29 | YARN_CONF_yarn_nodemanager_resource_memory___mb=8192
30 | YARN_CONF_yarn_nodemanager_resource_cpu___vcores=4
31 | YARN_CONF_yarn_nodemanager_disk___health___checker_max___disk___utilization___per___disk___percentage=98.5
32 | YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
33 | YARN_CONF_yarn_nodemanager_aux___services=mapreduce_shuffle
34 | 
35 | MAPRED_CONF_mapreduce_framework_name=yarn
36 | MAPRED_CONF_mapred_child_java_opts=-Xmx1024m
37 | MAPRED_CONF_mapreduce_map_memory_mb=512
38 | MAPRED_CONF_mapreduce_reduce_memory_mb=1024
39 | MAPRED_CONF_mapreduce_map_java_opts=-Xmx512m
40 | MAPRED_CONF_mapreduce_reduce_java_opts=-Xmx1024m
41 | 
42 | HIVE_SITE_CONF_javax_jdo_option_ConnectionURL=jdbc:postgresql://hive-metastore-postgresql/metastore
43 | HIVE_SITE_CONF_javax_jdo_option_ConnectionDriverName=org.postgresql.Driver
44 | HIVE_SITE_CONF_javax_jdo_option_ConnectionUserName=hive
45 | HIVE_SITE_CONF_javax_jdo_option_ConnectionPassword=hive
46 | HIVE_SITE_CONF_datanucleus_autoCreateSchema=false
47 | HIVE_SITE_CONF_hive_metastore_uris=thrift://hive-metastore:9083
48 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/PySparkShow.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "from pyspark.sql import SparkSession"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": null,
 15 |    "metadata": {},
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "#spark = SparkSession.builder.appName(\"TestApp\").master('spark://localhost:7077').getOrCreate()\n",
 19 |     "spark = SparkSession.builder.appName(\"TestApp\").getOrCreate()"
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "code",
 24 |    "execution_count": null,
 25 |    "metadata": {},
 26 |    "outputs": [],
 27 |    "source": [
 28 |     "spark"
 29 |    ]
 30 |   },
 31 |   {
 32 |    "cell_type": "code",
 33 |    "execution_count": null,
 34 |    "metadata": {},
 35 |    "outputs": [],
 36 |    "source": [
 37 |     "df = spark.read.parquet('taxi_data.parquet')"
 38 |    ]
 39 |   },
 40 |   {
 41 |    "cell_type": "code",
 42 |    "execution_count": null,
 43 |    "metadata": {},
 44 |    "outputs": [],
 45 |    "source": [
 46 |     "type(df)"
 47 |    ]
 48 |   },
 49 |   {
 50 |    "cell_type": "code",
 51 |    "execution_count": null,
 52 |    "metadata": {},
 53 |    "outputs": [],
 54 |    "source": [
 55 |     "type(df.rdd)"
 56 |    ]
 57 |   },
 58 |   {
 59 |    "cell_type": "code",
 60 |    "execution_count": null,
 61 |    "metadata": {},
 62 |    "outputs": [],
 63 |    "source": [
 64 |     "df.rdd.getNumPartitions()"
 65 |    ]
 66 |   },
 67 |   {
 68 |    "cell_type": "code",
 69 |    "execution_count": null,
 70 |    "metadata": {},
 71 |    "outputs": [],
 72 |    "source": [
 73 |     "df.repartition(16).write.parquet(\"tmp\")"
 74 |    ]
 75 |   },
 76 |   {
 77 |    "cell_type": "code",
 78 |    "execution_count": null,
 79 |    "metadata": {},
 80 |    "outputs": [],
 81 |    "source": [
 82 |     "ndf = spark.read.parquet('tmp')"
 83 |    ]
 84 |   },
 85 |   {
 86 |    "cell_type": "code",
 87 |    "execution_count": null,
 88 |    "metadata": {},
 89 |    "outputs": [],
 90 |    "source": [
 91 |     "ndf.count()"
 92 |    ]
 93 |   },
 94 |   {
 95 |    "cell_type": "code",
 96 |    "execution_count": null,
 97 |    "metadata": {},
 98 |    "outputs": [],
 99 |    "source": [
100 |     "df.count()"
101 |    ]
102 |   },
103 |   {
104 |    "cell_type": "code",
105 |    "execution_count": null,
106 |    "metadata": {},
107 |    "outputs": [],
108 |    "source": [
109 |     "df.groupBy(\"taxi_id\").count().explain()"
110 |    ]
111 |   },
112 |   {
113 |    "cell_type": "code",
114 |    "execution_count": null,
115 |    "metadata": {},
116 |    "outputs": [],
117 |    "source": [
118 |     "df.groupBy(\"taxi_id\").count().show()"
119 |    ]
120 |   },
121 |   {
122 |    "cell_type": "code",
123 |    "execution_count": null,
124 |    "metadata": {},
125 |    "outputs": [],
126 |    "source": [
127 |     "l = list(df.collect())"
128 |    ]
129 |   },
130 |   {
131 |    "cell_type": "code",
132 |    "execution_count": null,
133 |    "metadata": {},
134 |    "outputs": [],
135 |    "source": [
136 |     "type(l)"
137 |    ]
138 |   },
139 |   {
140 |    "cell_type": "code",
141 |    "execution_count": null,
142 |    "metadata": {},
143 |    "outputs": [],
144 |    "source": [
145 |     "l[0]"
146 |    ]
147 |   },
148 |   {
149 |    "cell_type": "code",
150 |    "execution_count": null,
151 |    "metadata": {},
152 |    "outputs": [],
153 |    "source": [
154 |     "df.toPandas().head()"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": null,
160 |    "metadata": {},
161 |    "outputs": [],
162 |    "source": [
163 |     "dfp = df.groupBy('taxi_id').count().orderBy('count', ascending=False).limit(1)"
164 |    ]
165 |   },
166 |   {
167 |    "cell_type": "code",
168 |    "execution_count": null,
169 |    "metadata": {},
170 |    "outputs": [],
171 |    "source": [
172 |     "type(dfp)"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "code",
177 |    "execution_count": null,
178 |    "metadata": {},
179 |    "outputs": [],
180 |    "source": [
181 |     "dfp.show()"
182 |    ]
183 |   },
184 |   {
185 |    "cell_type": "code",
186 |    "execution_count": null,
187 |    "metadata": {},
188 |    "outputs": [],
189 |    "source": [
190 |     "spark.read.parquet('taxi_data.parquet')\\\n",
191 |     "    .groupBy('taxi_id').count()\\\n",
192 |     "    .orderBy('count',ascending=False)\\\n",
193 |     "    .limit(1)\\\n",
194 |     "    .show()"
195 |    ]
196 |   },
197 |   {
198 |    "cell_type": "code",
199 |    "execution_count": null,
200 |    "metadata": {},
201 |    "outputs": [],
202 |    "source": [
203 |     "import pyspark.sql.functions as F\n",
204 |     "df = spark.read.parquet('taxi_data.parquet')"
205 |    ]
206 |   },
207 |   {
208 |    "cell_type": "code",
209 |    "execution_count": null,
210 |    "metadata": {},
211 |    "outputs": [],
212 |    "source": [
213 |     "df = df.filter(F.col('tips') > 0)\n",
214 |     "df.cache()\n",
215 |     "print('Count of events with tips: {}'.format(df.count()))\n",
216 |     "df.select('taxi_id', 'tips').groupBy(['taxi_id', 'tips']).sum('tips').show(5)"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": null,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "from pyspark import StorageLevel\n",
226 |     "df = spark.read.parquet('taxi_data.parquet')"
227 |    ]
228 |   },
229 |   {
230 |    "cell_type": "code",
231 |    "execution_count": null,
232 |    "metadata": {},
233 |    "outputs": [],
234 |    "source": [
235 |     "df.persist(StorageLevel.MEMORY_AND_DISK)"
236 |    ]
237 |   },
238 |   {
239 |    "cell_type": "code",
240 |    "execution_count": null,
241 |    "metadata": {},
242 |    "outputs": [],
243 |    "source": [
244 |     "df.persist(StorageLevel.DISK_ONLY)"
245 |    ]
246 |   },
247 |   {
248 |    "cell_type": "code",
249 |    "execution_count": null,
250 |    "metadata": {},
251 |    "outputs": [],
252 |    "source": [
253 |     "dch = df.cache() # == StorageLevel.MEMORY_ONLY_SER"
254 |    ]
255 |   },
256 |   {
257 |    "cell_type": "code",
258 |    "execution_count": null,
259 |    "metadata": {},
260 |    "outputs": [],
261 |    "source": [
262 |     "dch.show()"
263 |    ]
264 |   },
265 |   {
266 |    "cell_type": "code",
267 |    "execution_count": null,
268 |    "metadata": {},
269 |    "outputs": [],
270 |    "source": [
271 |     "df.groupBy('taxi_id') \\\n",
272 |     ".agg({'trip_start_timestamp': 'max', 'trip_start_timestamp': 'min'}) \\\n",
273 |     ".show()"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": null,
279 |    "metadata": {},
280 |    "outputs": [],
281 |    "source": [
282 |     "from pyspark.sql.functions import min, max, col\n",
283 |     "df.groupBy('taxi_id') \\\n",
284 |     ".agg(min(col('trip_start_timestamp')).alias('min_time'), max(col('trip_start_timestamp')).alias('max_time')) \\\n",
285 |     ".show()"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": null,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "spark.stop()"
295 |    ]
296 |   },
297 |   {
298 |    "cell_type": "code",
299 |    "execution_count": null,
300 |    "metadata": {},
301 |    "outputs": [],
302 |    "source": []
303 |   }
304 |  ],
305 |  "metadata": {
306 |   "kernelspec": {
307 |    "display_name": "Python 3",
308 |    "language": "python",
309 |    "name": "python3"
310 |   },
311 |   "language_info": {
312 |    "codemirror_mode": {
313 |     "name": "ipython",
314 |     "version": 3
315 |    },
316 |    "file_extension": ".py",
317 |    "mimetype": "text/x-python",
318 |    "name": "python",
319 |    "nbconvert_exporter": "python",
320 |    "pygments_lexer": "ipython3",
321 |    "version": "3.7.4"
322 |   }
323 |  },
324 |  "nbformat": 4,
325 |  "nbformat_minor": 2
326 | }
327 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/Spark/PySparkJob.py:
--------------------------------------------------------------------------------
 1 | import io
 2 | import sys
 3 | from pyspark.sql import SparkSession
 4 | 
 5 | 
 6 | def main():
 7 |     spark = SparkSession.builder.appName('PySparkJob').getOrCreate()
 8 | 
 9 | if __name__ == "__main__":
10 |     main()
11 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/Spark/docker-compose.yml:
--------------------------------------------------------------------------------
  1 | version: "3"
  2 | 
  3 | networks:
  4 |   default:
  5 |     driver: bridge
  6 | 
  7 | services:
  8 | # =============== Spark services ===============
  9 |   spark-master:
 10 |     image: bde2020/spark-master:2.4.1-hadoop2.7
 11 |     hostname: spark-master
 12 |     networks:
 13 |       - default
 14 |     environment:
 15 |       SPARK_PUBLIC_DNS: 0.0.0.0
 16 |       INIT_DAEMON_STEP: setup_spark
 17 |       #SPARK_DEPLOY_DEFAULTCORES: 2
 18 |     expose:
 19 |       - 4040
 20 |       - 7001
 21 |       - 7002
 22 |       - 7003
 23 |       - 7004
 24 |       - 7005
 25 |       - 7006
 26 |       - 7077
 27 |       - 6066
 28 |     ports:
 29 |       - 4040:4040
 30 |       - 6066:6066
 31 |       - 7077:7077
 32 |       - 8080:8080
 33 |       - 20021:20021
 34 |     volumes:
 35 |       - ./container-data/spark-master/conf:/conf
 36 |       - ./container-data/spark-master/data:/tmp/data
 37 |       - ./container-data/spark-master/work:/spark/work
 38 |       - ./container-data/spark-allnodes:/jar
 39 |       - ./container-data/spark-allnodes:/etc/spark/apps
 40 | 
 41 |   spark-worker-1:
 42 |     image: bde2020/spark-worker:2.4.1-hadoop2.7
 43 |     networks:
 44 |       - default
 45 |     depends_on:
 46 |       - "spark-master"
 47 |     hostname: spark-worker-1
 48 |     environment:
 49 |       SPARK_MASTER: spark://spark-master:7077
 50 |       SPARK_PUBLIC_DNS: 0.0.0.0
 51 |       SPARK_WORKER_CORES: 2
 52 |       SPARK_WORKER_MEMORY: 3g
 53 |       SPARK_WORKER_PORT: 8881
 54 |       SPARK_WORKER_WEBUI_PORT: 8081
 55 |     expose:
 56 |       - 7012
 57 |       - 7013
 58 |       - 7014
 59 |       - 7015
 60 |       - 7016
 61 |       - 8881
 62 |     ports:
 63 |       - 8081:8081
 64 |     volumes:
 65 |       - ./container-data/spark-worker-1/config:/conf
 66 |       - ./container-data/spark-worker-1/data:/tmp/data
 67 |       - ./container-data/spark-worker-1/work:/spark/work
 68 |       - ./container-data/spark-allnodes:/jar
 69 |       - ./container-data/spark-allnodes:/etc/spark/apps
 70 | 
 71 |   spark-worker-2:
 72 |     image: bde2020/spark-worker:2.4.1-hadoop2.7
 73 |     networks:
 74 |       - default
 75 |     depends_on:
 76 |       - "spark-master"
 77 |     hostname: spark-worker-2
 78 |     environment:
 79 |       SPARK_MASTER: spark://spark-master:7077
 80 |       SPARK_PUBLIC_DNS: 0.0.0.0
 81 |       SPARK_WORKER_CORES: 2
 82 |       SPARK_WORKER_MEMORY: 3g
 83 |       SPARK_WORKER_PORT: 8881
 84 |       SPARK_WORKER_WEBUI_PORT: 8081
 85 |     expose:
 86 |       - 7012
 87 |       - 7013
 88 |       - 7014
 89 |       - 7015
 90 |       - 7016
 91 |       - 8882
 92 |     ports:
 93 |       - 8082:8082
 94 |     volumes:
 95 |       - ./container-data/spark-worker-2/config:/conf
 96 |       - ./container-data/spark-worker-2/data:/tmp/data
 97 |       - ./container-data/spark-worker-2/work:/spark/work
 98 |       - ./container-data/spark-allnodes:/jar
 99 |       - ./container-data/spark-allnodes:/etc/spark/apps
100 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/Spark/help.txt:
--------------------------------------------------------------------------------
1 | Master UI: http://localhost:8080/
2 | spark-submit --master local --deploy-mode client PySparkJob.py
3 | spark-submit --master spark://localhost:7077 --deploy-mode client PySparkJob.py
4 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/Streaming/WordStream/WordStream.py:
--------------------------------------------------------------------------------
 1 | from pyspark.sql import SparkSession
 2 | 
 3 | 
 4 | def main():
 5 |     spark = SparkSession \
 6 |         .builder \
 7 |         .appName("WordCountStream") \
 8 |         .getOrCreate()
 9 | 
10 |     lines = spark \
11 |         .readStream \
12 |         .format("kafka") \
13 |         .option("kafka.bootstrap.servers", "localhost:9092,localhost:9093,localhost:9094") \
14 |         .option("subscribe", "words") \
15 |         .load()
16 | 
17 |     df = lines.selectExpr("CAST(value AS STRING)").alias("value")
18 | 
19 |     query = df \
20 |         .writeStream \
21 |         .outputMode("append") \
22 |         .format("console") \
23 |         .start()
24 | 
25 |     query.awaitTermination()
26 | 
27 | 
28 | if __name__ == "__main__":
29 |     main()
30 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/Streaming/WordStream/commands.txt:
--------------------------------------------------------------------------------
 1 | spark-submit --packages org.apache.spark:spark-sql-kafka-0-10_2.11:2.4.4 --master local[*] --deploy-mode client WordStream.py > log.txt
 2 | 
 3 | 
 4 | # Скачать Кафку тут
 5 | # https://kafka.apache.org/downloads (version 2.8)
 6 | 
 7 | #Kafka
 8 | kafka-topics --create --bootstrap-server localhost:9092,localhost:9093,localhost:9094 --replication-factor 1 --partitions 1 --topic words
 9 | 
10 | kafka-console-consumer --bootstrap-server localhost:9092,localhost:9093,localhost:9094 --topic words
11 | 
12 | kafka-console-producer --broker-list localhost:9092,localhost:9093,localhost:9094 --topic words
13 | 
14 | 
15 | #Kafka sh
16 | ./kafka-topics.sh --create --bootstrap-server localhost:9092,localhost:9093,localhost:9094 --replication-factor 1 --partitions 1 --topic words
17 | 
18 | ./kafka-console-consumer.sh --bootstrap-server localhost:9092,localhost:9093,localhost:9094 --topic words
19 | 
20 | ./kafka-console-producer.sh --broker-list localhost:9092,localhost:9093,localhost:9094 --topic words
21 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/Streaming/docker-compose.yml:
--------------------------------------------------------------------------------
 1 | version: "3"
 2 | 
 3 | networks:
 4 |   default:
 5 |     driver: bridge
 6 | 
 7 | services:
 8 | # =============== Zookeeper services ===============
 9 |   zoo1:
10 |     image: zookeeper:3.4.9
11 |     hostname: zoo1
12 |     networks:
13 |      - default
14 |     ports:
15 |       - "2181:2181"
16 |     environment:
17 |         ZOO_MY_ID: 1
18 |         ZOO_PORT: 2181
19 |         ZOO_SERVERS: server.1=zoo1:2888:3888
20 |     volumes:
21 |       - ./container-data/zoo1/data:/data
22 |       - ./container-data/zoo1/datalog:/datalog
23 | # =============== Kafka services ===============
24 |   kafka1:
25 |     image: confluentinc/cp-kafka:5.2.2
26 |     hostname: kafka1
27 |     networks:
28 |      - default
29 |     ports:
30 |       - "9092:9092"
31 |     environment:
32 |       KAFKA_ADVERTISED_LISTENERS: LISTENER_DOCKER_INTERNAL://kafka1:19092,LISTENER_DOCKER_EXTERNAL://${DOCKER_HOST_IP:-127.0.0.1}:9092
33 |       KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: LISTENER_DOCKER_INTERNAL:PLAINTEXT,LISTENER_DOCKER_EXTERNAL:PLAINTEXT
34 |       KAFKA_INTER_BROKER_LISTENER_NAME: LISTENER_DOCKER_INTERNAL
35 |       KAFKA_ZOOKEEPER_CONNECT: "zoo1:2181"
36 |       KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
37 |       KAFKA_BROKER_ID: 1
38 |       KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
39 |     volumes:
40 |       - ./container-data/kafka1/data:/var/lib/kafka/data
41 |       - ./container-data/kafka1/logs:/logs
42 |     depends_on:
43 |       - zoo1
44 | 
45 |   kafka2:
46 |     image: confluentinc/cp-kafka:5.2.2
47 |     hostname: kafka2
48 |     networks:
49 |      - default
50 |     ports:
51 |       - "9093:9093"
52 |     environment:
53 |       KAFKA_ADVERTISED_LISTENERS: LISTENER_DOCKER_INTERNAL://kafka2:19093,LISTENER_DOCKER_EXTERNAL://${DOCKER_HOST_IP:-127.0.0.1}:9093
54 |       KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: LISTENER_DOCKER_INTERNAL:PLAINTEXT,LISTENER_DOCKER_EXTERNAL:PLAINTEXT
55 |       KAFKA_INTER_BROKER_LISTENER_NAME: LISTENER_DOCKER_INTERNAL
56 |       KAFKA_ZOOKEEPER_CONNECT: "zoo1:2181"
57 |       KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
58 |       KAFKA_BROKER_ID: 2
59 |       KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
60 |     volumes:
61 |       - ./container-data/kafka2/data:/var/lib/kafka/data
62 |       - ./container-data/kafka2/logs:/logs
63 |     depends_on:
64 |       - zoo1
65 | 
66 |   kafka3:
67 |     image: confluentinc/cp-kafka:5.2.2
68 |     hostname: kafka3
69 |     networks:
70 |      - default
71 |     ports:
72 |       - "9094:9094"
73 |     environment:
74 |       KAFKA_ADVERTISED_LISTENERS: LISTENER_DOCKER_INTERNAL://kafka3:19094,LISTENER_DOCKER_EXTERNAL://${DOCKER_HOST_IP:-127.0.0.1}:9094
75 |       KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: LISTENER_DOCKER_INTERNAL:PLAINTEXT,LISTENER_DOCKER_EXTERNAL:PLAINTEXT
76 |       KAFKA_INTER_BROKER_LISTENER_NAME: LISTENER_DOCKER_INTERNAL
77 |       KAFKA_ZOOKEEPER_CONNECT: "zoo1:2181"
78 |       KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
79 |       KAFKA_BROKER_ID: 3
80 |       KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
81 |     volumes:
82 |       - ./container-data/kafka3/data:/var/lib/kafka/data
83 |       - ./container-data/kafka3/logs:/logs
84 |     depends_on:
85 |       - zoo1
86 | 


--------------------------------------------------------------------------------
/workshops/2. Spark/taxi_data.parquet:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AlexKbit/stepik-ds-course/db4e2f3f61ad74291d1fcacabd83e43dd78392a3/workshops/2. Spark/taxi_data.parquet


--------------------------------------------------------------------------------
/workshops/3. Airflow/container-data/airflow/dags/calculate_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.models import Variable
 4 | from airflow.operators.python_operator import PythonOperator
 5 | 
 6 | 
 7 | def load():
 8 |     return int(Variable.get('value'))
 9 | 
10 | 
11 | def multiply(**ctx):
12 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='load_task')
13 |     x = x * 25
14 |     return x
15 | 
16 | 
17 | def plus(**ctx):
18 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='multiply_task')
19 |     x = x + 5
20 |     return x
21 | 
22 | 
23 | def upload(**ctx):
24 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='plus_task')
25 |     Variable.set('result', x)
26 | 
27 | 
28 | dag = DAG(dag_id='calculation-dag',
29 |           start_date=datetime(2020, 3, 30),
30 |           schedule_interval='@once')
31 | 
32 | load_task = PythonOperator(task_id='load_task',
33 |                            python_callable=load,
34 |                            dag=dag)
35 | multiply_task = PythonOperator(task_id='multiply_task',
36 |                                python_callable=multiply,
37 |                                provide_context=True,
38 |                                dag=dag)
39 | plus_task = PythonOperator(task_id='plus_task',
40 |                            python_callable=plus,
41 |                            provide_context=True,
42 |                            dag=dag)
43 | upload_task = PythonOperator(task_id='upload_task',
44 |                              python_callable=upload,
45 |                              provide_context=True,
46 |                              dag=dag)
47 | 
48 | 
49 | load_task >> multiply_task >> plus_task >> upload_task
50 | 


--------------------------------------------------------------------------------
/workshops/3. Airflow/container-data/airflow/dags/calculate_parallel_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.models import Variable
 4 | from airflow.operators.python_operator import PythonOperator
 5 | 
 6 | 
 7 | def load():
 8 |     return int(Variable.get('value'))
 9 | 
10 | 
11 | def multiply(**ctx):
12 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='load_task')
13 |     x = x * 25
14 |     return x
15 | 
16 | 
17 | def plus5(**ctx):
18 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='multiply_task')
19 |     x = x + 5
20 |     return x
21 | 
22 | 
23 | def plus10(**ctx):
24 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='multiply_task')
25 |     x = x + 10
26 |     return x
27 | 
28 | 
29 | def upload1(**ctx):
30 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='plus5_task')
31 |     Variable.set('result1', x)
32 | 
33 | 
34 | def upload2(**ctx):
35 |     x = ctx['ti'].xcom_pull(key='return_value', task_ids='plus10_task')
36 |     Variable.set('result2', x)
37 | 
38 | 
39 | dag = DAG(dag_id='calculation-parallel-dag',
40 |           start_date=datetime(2020, 3, 30),
41 |           schedule_interval='@once')
42 | 
43 | load_task = PythonOperator(task_id='load_task',
44 |                            python_callable=load,
45 |                            dag=dag)
46 | multiply_task = PythonOperator(task_id='multiply_task',
47 |                                python_callable=multiply,
48 |                                provide_context=True,
49 |                                dag=dag)
50 | plus5_task = PythonOperator(task_id='plus5_task',
51 |                             python_callable=plus5,
52 |                             provide_context=True,
53 |                             dag=dag)
54 | plus10_task = PythonOperator(task_id='plus10_task',
55 |                              python_callable=plus10,
56 |                              provide_context=True,
57 |                              dag=dag)
58 | upload1_task = PythonOperator(task_id='upload1_task',
59 |                               python_callable=upload1,
60 |                               provide_context=True,
61 |                               dag=dag)
62 | upload2_task = PythonOperator(task_id='upload2_task',
63 |                               python_callable=upload2,
64 |                               provide_context=True,
65 |                               dag=dag)
66 | 
67 | 
68 | load_task >> multiply_task
69 | multiply_task >> plus5_task >> upload1_task
70 | multiply_task >> plus10_task >> upload2_task
71 | 


--------------------------------------------------------------------------------
/workshops/3. Airflow/container-data/airflow/dags/dummy_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.operators.dummy_operator import DummyOperator
 4 | 
 5 | 
 6 | dag = DAG(dag_id='dummy-dag',
 7 |           start_date=datetime(2020, 3, 30),
 8 |           schedule_interval='@once')
 9 | 
10 | t1 = DummyOperator(task_id='task1', dag=dag)
11 | t2 = DummyOperator(task_id='task2', dag=dag)
12 | t3 = DummyOperator(task_id='task3', dag=dag)
13 | t4 = DummyOperator(task_id='task4', dag=dag)
14 | t5 = DummyOperator(task_id='task5', dag=dag)
15 | t6 = DummyOperator(task_id='task6', dag=dag)
16 | t7 = DummyOperator(task_id='task7', dag=dag)
17 | t8 = DummyOperator(task_id='task8', dag=dag)
18 | t9 = DummyOperator(task_id='task9', dag=dag)
19 | t10 = DummyOperator(task_id='task10', dag=dag)
20 | t11 = DummyOperator(task_id='task11', dag=dag)
21 | t12 = DummyOperator(task_id='task12', dag=dag)
22 | t13 = DummyOperator(task_id='task13', dag=dag)
23 | t14 = DummyOperator(task_id='task14', dag=dag)
24 | t15 = DummyOperator(task_id='task15', dag=dag)
25 | 
26 | t1 >> t2
27 | t2 >> t3 >> t5 >> t7
28 | t2 >> t4 >> t6 >> t7
29 | t2 >> t8 >> t7
30 | t2 >> t9 >> t7
31 | t7 >> t10
32 | t10 >> t11 >> t15
33 | t10 >> t12 >> t15
34 | t10 >> t13 >> t15
35 | t10 >> t14 >> t15
36 | 


--------------------------------------------------------------------------------
/workshops/3. Airflow/container-data/airflow/dags/hello_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG, AirflowException
 3 | from datetime import datetime
 4 | from airflow.operators.python_operator import PythonOperator
 5 | from airflow.utils.trigger_rule import TriggerRule
 6 | 
 7 | 
 8 | def print_1():
 9 |     return 'Step 1'
10 | 
11 | 
12 | def print_2():
13 |     raise AirflowException('Oops!') #Uncomment to make error
14 |     return 'Step 2'
15 | 
16 | 
17 | def print_3():
18 |     return 'Step 3'
19 | 
20 | 
21 | def print_hello():
22 |     return 'Hello Wolrd'
23 | 
24 | 
25 | dag = DAG('hello-world-dag',
26 |           start_date=datetime(2020, 3, 30),
27 |           description='Hello world example',
28 |           schedule_interval='@once')
29 | 
30 | step1 = PythonOperator(task_id='step1', python_callable=print_1, dag=dag)
31 | step2 = PythonOperator(task_id='step2', python_callable=print_2, dag=dag)
32 | step3 = PythonOperator(task_id='step3', python_callable=print_3, dag=dag)
33 | hello_operator = PythonOperator(task_id='hello_task',
34 |                                 python_callable=print_hello,
35 |                                 trigger_rule=TriggerRule.ONE_SUCCESS, #Uncomment to skip error
36 |                                 dag=dag)
37 | 
38 | step1 >> [step2, step3]
39 | step2 >> hello_operator
40 | step3 >> hello_operator
41 | 


--------------------------------------------------------------------------------
/workshops/3. Airflow/container-data/airflow/dags/test_dag.py:
--------------------------------------------------------------------------------
 1 | from datetime import datetime
 2 | from airflow import DAG
 3 | from airflow.operators.dummy_operator import DummyOperator
 4 | 
 5 | 
 6 | dag = DAG(dag_id='test-dag-2',
 7 |           start_date=datetime(2022, 3, 30),
 8 |           max_active_runs = 1,
 9 |           schedule_interval='@daily')
10 | 
11 | t1 = DummyOperator(task_id='task1', dag=dag)
12 | t2 = DummyOperator(task_id='task2', dag=dag)
13 | t3 = DummyOperator(task_id='task3', dag=dag)
14 | 
15 | t1 >> t2 >> t3
16 | 


--------------------------------------------------------------------------------
/workshops/3. Airflow/docker-compose.yaml:
--------------------------------------------------------------------------------
 1 | version: '2.1'
 2 | services:
 3 |     redis:
 4 |         image: 'redis:5.0.5'
 5 |         # command: redis-server --requirepass redispass
 6 | 
 7 |     postgres:
 8 |         image: postgres:9.6
 9 |         environment:
10 |             - POSTGRES_USER=airflow
11 |             - POSTGRES_PASSWORD=airflow
12 |             - POSTGRES_DB=airflow
13 |         # Uncomment these lines to persist data on the local filesystem.
14 |         #     - PGDATA=/var/lib/postgresql/data/pgdata
15 |         # volumes:
16 |         #     - ./pgdata:/var/lib/postgresql/data/pgdata
17 | 
18 |     webserver:
19 |         image: puckel/docker-airflow:1.10.4
20 |         restart: always
21 |         depends_on:
22 |             - postgres
23 |             - redis
24 |         environment:
25 |             - LOAD_EX=n
26 |             - FERNET_KEY=46BKJoQYlPPOexq0OhDZnIlNepKFf87WFwLbfzqDDho=
27 |             - EXECUTOR=Celery
28 |             # - POSTGRES_USER=airflow
29 |             # - POSTGRES_PASSWORD=airflow
30 |             # - POSTGRES_DB=airflow
31 |             # - REDIS_PASSWORD=redispass
32 |         volumes:
33 |             - ./container-data/airflow/dags:/usr/local/airflow/dags
34 |             # Uncomment to include custom plugins
35 |             # - ./plugins:/usr/local/airflow/plugins
36 |         ports:
37 |             - "8080:8080"
38 |         command: webserver
39 |         healthcheck:
40 |             test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-webserver.pid ]"]
41 |             interval: 30s
42 |             timeout: 30s
43 |             retries: 3
44 | 
45 |     flower:
46 |         image: puckel/docker-airflow:1.10.4
47 |         restart: always
48 |         depends_on:
49 |             - redis
50 |         environment:
51 |             - EXECUTOR=Celery
52 |             # - REDIS_PASSWORD=redispass
53 |         ports:
54 |             - "5555:5555"
55 |         command: flower
56 | 
57 |     scheduler:
58 |         image: puckel/docker-airflow:1.10.4
59 |         restart: always
60 |         depends_on:
61 |             - webserver
62 |         volumes:
63 |             - ./container-data/airflow/dags:/usr/local/airflow/dags
64 |             # Uncomment to include custom plugins
65 |             # - ./plugins:/usr/local/airflow/plugins
66 |         environment:
67 |             - LOAD_EX=n
68 |             - FERNET_KEY=46BKJoQYlPPOexq0OhDZnIlNepKFf87WFwLbfzqDDho=
69 |             - EXECUTOR=Celery
70 |             # - POSTGRES_USER=airflow
71 |             # - POSTGRES_PASSWORD=airflow
72 |             # - POSTGRES_DB=airflow
73 |             # - REDIS_PASSWORD=redispass
74 |         command: scheduler
75 | 
76 |     worker:
77 |         image: puckel/docker-airflow:1.10.4
78 |         restart: always
79 |         depends_on:
80 |             - scheduler
81 |         volumes:
82 |             - ./container-data/airflow/dags:/usr/local/airflow/dags
83 |             # Uncomment to include custom plugins
84 |             # - ./plugins:/usr/local/airflow/plugins
85 |         environment:
86 |             - FERNET_KEY=46BKJoQYlPPOexq0OhDZnIlNepKFf87WFwLbfzqDDho=
87 |             - EXECUTOR=Celery
88 |             # - POSTGRES_USER=airflow
89 |             # - POSTGRES_PASSWORD=airflow
90 |             # - POSTGRES_DB=airflow
91 |             # - REDIS_PASSWORD=redispass
92 |         command: worker
93 | 


--------------------------------------------------------------------------------