├── zappa_settings.json
├── readme.md
├── requirements.txt
├── jupytext_conversion
└── transform_format.py
├── app.py
├── .gitignore
└── transform_format.ipynb
/zappa_settings.json:
--------------------------------------------------------------------------------
1 | {
2 | "dev": {
3 | "app_function": "app.app",
4 | "aws_region": "eu-central-1",
5 | "profile_name": "default",
6 | "project_name": "pandas-transform-format",
7 | "runtime": "python3.7",
8 | "s3_bucket": "zappa-pandas-transform-format"
9 | }
10 | }
--------------------------------------------------------------------------------
/readme.md:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
CSV Excel to other formats
5 |
6 |
7 | Convert Excel (csv) file to other formats
8 |
9 | Explore the tutorial »
10 |
11 |
12 |
13 |
14 |
15 | ---
16 |
17 | 
18 |
19 | # About The Project
20 |
21 | This is the API Code for my tutorial article:
22 | - https://github.com/Createdd/Writing/blob/master/2020/articles/pythonApi.md
23 |
24 | It paints a picture for developing a Python API from start to finish and provides help in more difficult areas like the setup with AWS and RapidAPI.
25 |
26 | You will find the end result on Rapidapi:
27 |
28 | - https://rapidapi.com/Createdd/api/excel-to-other-formats
29 |
30 | If you found this article helpful let me know and/or buy the functionality on Rapidapi to show support.
31 |
32 |
33 |
34 | ## Data
35 |
36 | For example data I used the [titanic dataset](https://www.kaggle.com/c/titanic).
37 |
38 | ## Built With
39 |
40 | - Github (Code hosting),
41 | - Anaconda (Dependency and environment management),
42 | - Jupyter Notebook (code development and documentaion),
43 | - Python (programming language),
44 | - AWS (deployment),
45 | - RapidAPI (market to sell)
46 |
47 |
48 | # About the author
49 |
50 | Daniel is an entrepreneur, software developer and lawyer. His knowledge and interests currently revolve around programming machine learning applications and all its related aspects.
51 |
52 | **Connect on:**
53 | - [LinkedIn](https://www.linkedin.com/in/createdd)
54 | - [Github](https://github.com/Createdd)
55 | - [Medium](https://medium.com/@createdd)
56 | - [Twitter](https://twitter.com/_createdd)
57 | - [Instagram](https://www.instagram.com/create.dd/)
--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | appnope==0.1.0
2 | argcomplete==1.12.0
3 | argon2-cffi==20.1.0
4 | attrs==20.1.0
5 | autopep8==1.5.4
6 | backcall==0.2.0
7 | bleach==3.1.5
8 | boto3==1.14.51
9 | botocore==1.17.51
10 | certifi==2020.6.20
11 | cffi==1.14.2
12 | cfn-flip==1.2.3
13 | chardet==3.0.4
14 | click==7.1.2
15 | decorator==4.4.2
16 | defusedxml==0.6.0
17 | docutils==0.15.2
18 | durationpy==0.5
19 | entrypoints==0.3
20 | Flask==1.1.2
21 | future==0.18.2
22 | hjson==3.0.1
23 | idna==2.10
24 | importlib-metadata==1.7.0
25 | ipykernel==5.3.4
26 | ipython==7.17.0
27 | ipython-genutils==0.2.0
28 | itsdangerous==1.1.0
29 | jedi==0.17.2
30 | Jinja2==2.11.2
31 | jmespath==0.10.0
32 | jsonschema==3.2.0
33 | jupyter-client==6.1.7
34 | jupyter-core==4.6.3
35 | jupytext==1.5.2
36 | kappa==0.6.0
37 | lml==0.0.9
38 | MarkupSafe==1.1.1
39 | mistune==0.8.4
40 | nbconvert==5.6.1
41 | nbformat==5.0.7
42 | notebook==6.1.3
43 | numexpr==2.7.1
44 | numpy==1.19.1
45 | packaging==20.4
46 | pandas==1.1.1
47 | pandocfilters==1.4.2
48 | parso==0.7.1
49 | pexpect==4.8.0
50 | pickleshare==0.7.5
51 | pip-tools==5.3.1
52 | placebo==0.9.0
53 | prometheus-client==0.8.0
54 | prompt-toolkit==3.0.6
55 | ptyprocess==0.6.0
56 | pyarrow==1.0.1
57 | pycodestyle==2.6.0
58 | pycparser==2.20
59 | pyexcel==0.6.4
60 | pyexcel-io==0.5.20
61 | pyexcel-webio==0.1.4
62 | Pygments==2.6.1
63 | pyparsing==2.4.7
64 | pyrsistent==0.16.0
65 | python-dateutil==2.6.1
66 | python-slugify==4.0.1
67 | pytz==2020.1
68 | PyYAML==5.3.1
69 | pyzmq==19.0.2
70 | requests==2.24.0
71 | s3transfer==0.3.3
72 | Send2Trash==1.5.0
73 | six==1.15.0
74 | tables==3.6.1
75 | terminado==0.8.3
76 | testpath==0.4.4
77 | text-unidecode==1.3
78 | texttable==1.6.2
79 | toml==0.10.1
80 | tornado==6.0.4
81 | tqdm==4.48.2
82 | traitlets==4.3.3
83 | troposphere==2.6.2
84 | urllib3==1.25.10
85 | wcwidth==0.2.5
86 | webencodings==0.5.1
87 | Werkzeug==0.16.1
88 | wsgi-request-logger==0.4.6
89 | zappa==0.51.0
90 | zipp==3.1.0
91 |
--------------------------------------------------------------------------------
/jupytext_conversion/transform_format.py:
--------------------------------------------------------------------------------
1 | # ---
2 | # jupyter:
3 | # jupytext:
4 | # text_representation:
5 | # extension: .py
6 | # format_name: light
7 | # format_version: '1.5'
8 | # jupytext_version: 1.5.2
9 | # kernelspec:
10 | # display_name: Python 3.7.6 64-bit
11 | # language: python
12 | # name: python37664bitcec5513a60ce49909c4b87b3ad0ec34d
13 | # ---
14 |
15 | # +
16 | import sys # module for python interpreter
17 | sys.path.append('../') # necessary for relative import of utils file e.g.
18 |
19 | import os
20 | import requests
21 |
22 | import pandas as pd
23 |
24 |
25 | from IPython.core.interactiveshell import InteractiveShell
26 | # # %load_ext autoreload
27 | # # %autoreload 2
28 | # # # %matplotlib inline
29 | # # %config IPCompleter.greedy=True
30 |
31 | # pd.options.display.max_columns = None
32 | # pd.options.display.max_rows = 200
33 | # sns.set_palette("bright")
34 | # sns.set(style="darkgrid")
35 |
36 | InteractiveShell.ast_node_interactivity = "all"
37 |
38 |
39 | # -
40 |
41 | # # Load dataset
42 |
43 | # +
44 | def download(url: str, dest_folder: str):
45 | if not os.path.exists(dest_folder):
46 | os.makedirs(dest_folder) # create folder if it does not exist
47 |
48 | filename = url.split('/')[-1].replace(" ", "_") # be careful with file names
49 | file_path = os.path.join(dest_folder, filename)
50 |
51 | r = requests.get(url, stream=True)
52 | if r.ok:
53 | print("saving to", os.path.abspath(file_path))
54 | with open(file_path, 'wb') as f:
55 | for chunk in r.iter_content(chunk_size=1024 * 8):
56 | if chunk:
57 | f.write(chunk)
58 | f.flush()
59 | os.fsync(f.fileno())
60 | else: # HTTP status code 4XX/5XX
61 | print("Download failed: status code {}\n{}".format(r.status_code, r.text))
62 |
63 |
64 | download('https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/stuff/titanic.csv', './data')
65 |
66 | # -
67 |
68 | # # Transform data
69 |
70 | # +
71 | df = pd.read_csv('./data/titanic.csv')
72 | # df = pd.read_json('./data/titanic.json')
73 |
74 | df.to_json(r'./data/titanic.json')
75 |
76 | df.columns
77 | df
78 | # -
79 |
80 |
81 |
--------------------------------------------------------------------------------
/app.py:
--------------------------------------------------------------------------------
1 | import json
2 | import os
3 |
4 | import pandas as pd
5 | from flask import Flask, request, send_from_directory, abort
6 |
7 |
8 | app = Flask(__name__)
9 | UPLOAD_DIRECTORY = "."
10 |
11 | conversions = ['h5', 'pkl', 'feather', 'parquet' ]
12 |
13 | @app.route('/', methods=['GET'])
14 | def home():
15 | return 'This app provides data format transformation!'
16 |
17 |
18 | @app.route('/download', methods=['GET', 'POST'])
19 | def download_file():
20 | if request.method == 'POST':
21 | provided_data = request.files.get('file')
22 | if provided_data is None:
23 | return 'Please enter valid excel format ', 400
24 | provided_format = request.form.get('format')
25 | if provided_format is None:
26 | return f'Please enter valid format to convert.', 400
27 | if provided_format not in conversions:
28 | return f'Please enter valid format to convert. Can be {list(conversions)}', 400
29 |
30 | df = pd.read_csv(provided_data)
31 | file_name = f'converted.{provided_format}'
32 | path = f'./{file_name}'
33 |
34 | if provided_format == 'h5':
35 | df.to_hdf(
36 | path,
37 | file_name,
38 | mode='w')
39 | elif provided_format == 'pkl':
40 | df.to_pickle(path)
41 | elif provided_format == 'parquet':
42 | df.to_pickle(path)
43 | elif provided_format == 'feather':
44 | df.to_pickle(path)
45 |
46 | try:
47 | return send_from_directory(UPLOAD_DIRECTORY, filename=file_name, as_attachment=True)
48 | except FileNotFoundError:
49 | abort(404)
50 | finally:
51 | remove_file(path)
52 |
53 | def remove_file(new_file):
54 | path = os.path.join(UPLOAD_DIRECTORY, new_file)
55 | os.remove(path)
56 |
57 |
58 | @app.route('/get_json', methods=['GET', 'POST'])
59 | def upload_file():
60 | if request.method == 'POST':
61 | provided_data = request.files.get('file')
62 | if provided_data is None:
63 | return 'Please enter valid excel format ', 400
64 |
65 | data = provided_data
66 | df = pd.read_csv(data)
67 | transformed = df.to_json()
68 |
69 | result = {
70 | 'result': transformed,
71 | }
72 |
73 | json.dumps(result)
74 |
75 | return result
76 |
77 | if __name__ == '__main__':
78 | app.run()
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | data/
2 | # .vscode/
3 | # keys/
4 | # .aws_shortcut
5 | *.h5
6 |
7 |
8 | # Byte-compiled / optimized / DLL files
9 | __pycache__/
10 | *.py[cod]
11 | *$py.class
12 |
13 | # C extensions
14 | *.so
15 |
16 | # Distribution / packaging
17 | .Python
18 | build/
19 | develop-eggs/
20 | dist/
21 | downloads/
22 | eggs/
23 | .eggs/
24 | lib/
25 | lib64/
26 | parts/
27 | sdist/
28 | var/
29 | wheels/
30 | share/python-wheels/
31 | *.egg-info/
32 | .installed.cfg
33 | *.egg
34 | MANIFEST
35 |
36 | # PyInstaller
37 | # Usually these files are written by a python script from a template
38 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
39 | *.manifest
40 | *.spec
41 |
42 | # Installer logs
43 | pip-log.txt
44 | pip-delete-this-directory.txt
45 |
46 | # Unit test / coverage reports
47 | htmlcov/
48 | .tox/
49 | .nox/
50 | .coverage
51 | .coverage.*
52 | .cache
53 | nosetests.xml
54 | coverage.xml
55 | *.cover
56 | *.py,cover
57 | .hypothesis/
58 | .pytest_cache/
59 | cover/
60 |
61 | # Translations
62 | *.mo
63 | *.pot
64 |
65 | # Django stuff:
66 | *.log
67 | local_settings.py
68 | db.sqlite3
69 | db.sqlite3-journal
70 |
71 | # Flask stuff:
72 | instance/
73 | .webassets-cache
74 |
75 | # Scrapy stuff:
76 | .scrapy
77 |
78 | # Sphinx documentation
79 | docs/_build/
80 |
81 | # PyBuilder
82 | .pybuilder/
83 | target/
84 |
85 | # Jupyter Notebook
86 | .ipynb_checkpoints
87 |
88 | # IPython
89 | profile_default/
90 | ipython_config.py
91 |
92 | # pyenv
93 | # For a library or package, you might want to ignore these files since the code is
94 | # intended to run in multiple environments; otherwise, check them in:
95 | # .python-version
96 |
97 | # pipenv
98 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
99 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
100 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
101 | # install all needed dependencies.
102 | #Pipfile.lock
103 |
104 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
105 | __pypackages__/
106 |
107 | # Celery stuff
108 | celerybeat-schedule
109 | celerybeat.pid
110 |
111 | # SageMath parsed files
112 | *.sage.py
113 |
114 | # Environments
115 | .env
116 | .venv
117 | env/
118 | venv/
119 | ENV/
120 | env.bak/
121 | venv.bak/
122 |
123 | # Spyder project settings
124 | .spyderproject
125 | .spyproject
126 |
127 | # Rope project settings
128 | .ropeproject
129 |
130 | # mkdocs documentation
131 | /site
132 |
133 | # mypy
134 | .mypy_cache/
135 | .dmypy.json
136 | dmypy.json
137 |
138 | # Pyre type checker
139 | .pyre/
140 |
141 | # pytype static type analyzer
142 | .pytype/
143 |
144 | # Cython debug symbols
145 | cython_debug/
146 |
147 | # General
148 | .DS_Store
149 | .AppleDouble
150 | .LSOverride
151 |
152 | # Icon must end with two \r
153 | Icon
154 |
155 |
156 | # Thumbnails
157 | ._*
158 |
159 | # Files that might appear in the root of a volume
160 | .DocumentRevisions-V100
161 | .fseventsd
162 | .Spotlight-V100
163 | .TemporaryItems
164 | .Trashes
165 | .VolumeIcon.icns
166 | .com.apple.timemachine.donotpresent
167 |
168 | # Directories potentially created on remote AFP share
169 | .AppleDB
170 | .AppleDesktop
171 | Network Trash Folder
172 | Temporary Items
173 | .apdisk
174 |
--------------------------------------------------------------------------------
/transform_format.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "code",
5 | "execution_count": 1,
6 | "metadata": {
7 | "ExecuteTime": {
8 | "end_time": "2020-09-01T15:59:55.450296Z",
9 | "start_time": "2020-09-01T15:59:54.651335Z"
10 | }
11 | },
12 | "outputs": [],
13 | "source": [
14 | "import sys # module for python interpreter\n",
15 | "sys.path.append('../') # necessary for relative import of utils file e.g.\n",
16 | "\n",
17 | "import os\n",
18 | "import requests\n",
19 | "\n",
20 | "import pandas as pd\n",
21 | "\n",
22 | "from IPython.core.interactiveshell import InteractiveShell\n",
23 | "# %load_ext autoreload\n",
24 | "# %autoreload 2\n",
25 | "# # %matplotlib inline\n",
26 | "# %config IPCompleter.greedy=True\n",
27 | "\n",
28 | "# pd.options.display.max_columns = None\n",
29 | "# pd.options.display.max_rows = 200\n",
30 | "# sns.set_palette(\"bright\")\n",
31 | "# sns.set(style=\"darkgrid\")\n",
32 | "\n",
33 | "InteractiveShell.ast_node_interactivity = \"all\""
34 | ]
35 | },
36 | {
37 | "cell_type": "markdown",
38 | "metadata": {},
39 | "source": [
40 | "# Load dataset"
41 | ]
42 | },
43 | {
44 | "cell_type": "code",
45 | "execution_count": 2,
46 | "metadata": {
47 | "ExecuteTime": {
48 | "end_time": "2020-09-01T15:59:55.461121Z",
49 | "start_time": "2020-09-01T15:59:55.453927Z"
50 | }
51 | },
52 | "outputs": [],
53 | "source": [
54 | "def download(url: str, dest_folder: str):\n",
55 | " if not os.path.exists(dest_folder):\n",
56 | " os.makedirs(dest_folder) \n",
57 | "\n",
58 | " filename = url.split('/')[-1].replace(\" \", \"_\") \n",
59 | " file_path = os.path.join(dest_folder, filename)\n",
60 | "\n",
61 | " r = requests.get(url, stream=True)\n",
62 | " if r.ok:\n",
63 | " print(\"saving to\", os.path.abspath(file_path))\n",
64 | " with open(file_path, 'wb') as f:\n",
65 | " for chunk in r.iter_content(chunk_size=1024 * 8):\n",
66 | " if chunk:\n",
67 | " f.write(chunk)\n",
68 | " f.flush()\n",
69 | " os.fsync(f.fileno())\n",
70 | " else: \n",
71 | " print(\"Download failed: status code {}\\n{}\".format(r.status_code, r.text))"
72 | ]
73 | },
74 | {
75 | "cell_type": "code",
76 | "execution_count": 3,
77 | "metadata": {
78 | "ExecuteTime": {
79 | "end_time": "2020-09-01T15:59:56.623693Z",
80 | "start_time": "2020-09-01T15:59:55.463528Z"
81 | }
82 | },
83 | "outputs": [
84 | {
85 | "name": "stdout",
86 | "output_type": "stream",
87 | "text": [
88 | "saving to /Users/danieldeutsch/Desktop/code/pandas_transform_format/data/titanic.csv\n"
89 | ]
90 | }
91 | ],
92 | "source": [
93 | "url_to_titanic_data = 'https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/stuff/titanic.csv'\n",
94 | "\n",
95 | "download(url_to_titanic_data,'./data')"
96 | ]
97 | },
98 | {
99 | "cell_type": "markdown",
100 | "metadata": {},
101 | "source": [
102 | "# Transform data"
103 | ]
104 | },
105 | {
106 | "cell_type": "code",
107 | "execution_count": 37,
108 | "metadata": {
109 | "ExecuteTime": {
110 | "end_time": "2020-09-03T07:05:22.955957Z",
111 | "start_time": "2020-09-03T07:05:22.932351Z"
112 | }
113 | },
114 | "outputs": [
115 | {
116 | "data": {
117 | "text/html": [
118 | "\n",
119 | "\n",
132 | "
\n",
133 | " \n",
134 | " \n",
135 | " | \n",
136 | " Survived | \n",
137 | " Pclass | \n",
138 | " Name | \n",
139 | " Sex | \n",
140 | " Age | \n",
141 | " Siblings/Spouses Aboard | \n",
142 | " Parents/Children Aboard | \n",
143 | " Fare | \n",
144 | "
\n",
145 | " \n",
146 | " \n",
147 | " \n",
148 | " | 0 | \n",
149 | " 0 | \n",
150 | " 3 | \n",
151 | " Mr. Owen Harris Braund | \n",
152 | " male | \n",
153 | " 22.0 | \n",
154 | " 1 | \n",
155 | " 0 | \n",
156 | " 7.2500 | \n",
157 | "
\n",
158 | " \n",
159 | " | 1 | \n",
160 | " 1 | \n",
161 | " 1 | \n",
162 | " Mrs. John Bradley (Florence Briggs Thayer) Cum... | \n",
163 | " female | \n",
164 | " 38.0 | \n",
165 | " 1 | \n",
166 | " 0 | \n",
167 | " 71.2833 | \n",
168 | "
\n",
169 | " \n",
170 | " | 2 | \n",
171 | " 1 | \n",
172 | " 3 | \n",
173 | " Miss. Laina Heikkinen | \n",
174 | " female | \n",
175 | " 26.0 | \n",
176 | " 0 | \n",
177 | " 0 | \n",
178 | " 7.9250 | \n",
179 | "
\n",
180 | " \n",
181 | " | 3 | \n",
182 | " 1 | \n",
183 | " 1 | \n",
184 | " Mrs. Jacques Heath (Lily May Peel) Futrelle | \n",
185 | " female | \n",
186 | " 35.0 | \n",
187 | " 1 | \n",
188 | " 0 | \n",
189 | " 53.1000 | \n",
190 | "
\n",
191 | " \n",
192 | " | 4 | \n",
193 | " 0 | \n",
194 | " 3 | \n",
195 | " Mr. William Henry Allen | \n",
196 | " male | \n",
197 | " 35.0 | \n",
198 | " 0 | \n",
199 | " 0 | \n",
200 | " 8.0500 | \n",
201 | "
\n",
202 | " \n",
203 | " | ... | \n",
204 | " ... | \n",
205 | " ... | \n",
206 | " ... | \n",
207 | " ... | \n",
208 | " ... | \n",
209 | " ... | \n",
210 | " ... | \n",
211 | " ... | \n",
212 | "
\n",
213 | " \n",
214 | " | 882 | \n",
215 | " 0 | \n",
216 | " 2 | \n",
217 | " Rev. Juozas Montvila | \n",
218 | " male | \n",
219 | " 27.0 | \n",
220 | " 0 | \n",
221 | " 0 | \n",
222 | " 13.0000 | \n",
223 | "
\n",
224 | " \n",
225 | " | 883 | \n",
226 | " 1 | \n",
227 | " 1 | \n",
228 | " Miss. Margaret Edith Graham | \n",
229 | " female | \n",
230 | " 19.0 | \n",
231 | " 0 | \n",
232 | " 0 | \n",
233 | " 30.0000 | \n",
234 | "
\n",
235 | " \n",
236 | " | 884 | \n",
237 | " 0 | \n",
238 | " 3 | \n",
239 | " Miss. Catherine Helen Johnston | \n",
240 | " female | \n",
241 | " 7.0 | \n",
242 | " 1 | \n",
243 | " 2 | \n",
244 | " 23.4500 | \n",
245 | "
\n",
246 | " \n",
247 | " | 885 | \n",
248 | " 1 | \n",
249 | " 1 | \n",
250 | " Mr. Karl Howell Behr | \n",
251 | " male | \n",
252 | " 26.0 | \n",
253 | " 0 | \n",
254 | " 0 | \n",
255 | " 30.0000 | \n",
256 | "
\n",
257 | " \n",
258 | " | 886 | \n",
259 | " 0 | \n",
260 | " 3 | \n",
261 | " Mr. Patrick Dooley | \n",
262 | " male | \n",
263 | " 32.0 | \n",
264 | " 0 | \n",
265 | " 0 | \n",
266 | " 7.7500 | \n",
267 | "
\n",
268 | " \n",
269 | "
\n",
270 | "
887 rows × 8 columns
\n",
271 | "
\n",
354 | "\n",
367 | "
\n",
368 | " \n",
369 | " \n",
370 | " | \n",
371 | " Survived | \n",
372 | " Pclass | \n",
373 | " Name | \n",
374 | " Sex | \n",
375 | " Age | \n",
376 | " Siblings/Spouses Aboard | \n",
377 | " Parents/Children Aboard | \n",
378 | " Fare | \n",
379 | "
\n",
380 | " \n",
381 | " \n",
382 | " \n",
383 | " | 0 | \n",
384 | " 0 | \n",
385 | " 3 | \n",
386 | " Mr. Owen Harris Braund | \n",
387 | " male | \n",
388 | " 22.0 | \n",
389 | " 1 | \n",
390 | " 0 | \n",
391 | " 7.2500 | \n",
392 | "
\n",
393 | " \n",
394 | " | 1 | \n",
395 | " 1 | \n",
396 | " 1 | \n",
397 | " Mrs. John Bradley (Florence Briggs Thayer) Cum... | \n",
398 | " female | \n",
399 | " 38.0 | \n",
400 | " 1 | \n",
401 | " 0 | \n",
402 | " 71.2833 | \n",
403 | "
\n",
404 | " \n",
405 | " | 2 | \n",
406 | " 1 | \n",
407 | " 3 | \n",
408 | " Miss. Laina Heikkinen | \n",
409 | " female | \n",
410 | " 26.0 | \n",
411 | " 0 | \n",
412 | " 0 | \n",
413 | " 7.9250 | \n",
414 | "
\n",
415 | " \n",
416 | " | 3 | \n",
417 | " 1 | \n",
418 | " 1 | \n",
419 | " Mrs. Jacques Heath (Lily May Peel) Futrelle | \n",
420 | " female | \n",
421 | " 35.0 | \n",
422 | " 1 | \n",
423 | " 0 | \n",
424 | " 53.1000 | \n",
425 | "
\n",
426 | " \n",
427 | " | 4 | \n",
428 | " 0 | \n",
429 | " 3 | \n",
430 | " Mr. William Henry Allen | \n",
431 | " male | \n",
432 | " 35.0 | \n",
433 | " 0 | \n",
434 | " 0 | \n",
435 | " 8.0500 | \n",
436 | "
\n",
437 | " \n",
438 | " | ... | \n",
439 | " ... | \n",
440 | " ... | \n",
441 | " ... | \n",
442 | " ... | \n",
443 | " ... | \n",
444 | " ... | \n",
445 | " ... | \n",
446 | " ... | \n",
447 | "
\n",
448 | " \n",
449 | " | 882 | \n",
450 | " 0 | \n",
451 | " 2 | \n",
452 | " Rev. Juozas Montvila | \n",
453 | " male | \n",
454 | " 27.0 | \n",
455 | " 0 | \n",
456 | " 0 | \n",
457 | " 13.0000 | \n",
458 | "
\n",
459 | " \n",
460 | " | 883 | \n",
461 | " 1 | \n",
462 | " 1 | \n",
463 | " Miss. Margaret Edith Graham | \n",
464 | " female | \n",
465 | " 19.0 | \n",
466 | " 0 | \n",
467 | " 0 | \n",
468 | " 30.0000 | \n",
469 | "
\n",
470 | " \n",
471 | " | 884 | \n",
472 | " 0 | \n",
473 | " 3 | \n",
474 | " Miss. Catherine Helen Johnston | \n",
475 | " female | \n",
476 | " 7.0 | \n",
477 | " 1 | \n",
478 | " 2 | \n",
479 | " 23.4500 | \n",
480 | "
\n",
481 | " \n",
482 | " | 885 | \n",
483 | " 1 | \n",
484 | " 1 | \n",
485 | " Mr. Karl Howell Behr | \n",
486 | " male | \n",
487 | " 26.0 | \n",
488 | " 0 | \n",
489 | " 0 | \n",
490 | " 30.0000 | \n",
491 | "
\n",
492 | " \n",
493 | " | 886 | \n",
494 | " 0 | \n",
495 | " 3 | \n",
496 | " Mr. Patrick Dooley | \n",
497 | " male | \n",
498 | " 32.0 | \n",
499 | " 0 | \n",
500 | " 0 | \n",
501 | " 7.7500 | \n",
502 | "
\n",
503 | " \n",
504 | "
\n",
505 | "
887 rows × 8 columns
\n",
506 | "
\n",
606 | "\n",
619 | "
\n",
620 | " \n",
621 | " \n",
622 | " | \n",
623 | " Survived | \n",
624 | " Pclass | \n",
625 | " Name | \n",
626 | " Sex | \n",
627 | " Age | \n",
628 | " Siblings/Spouses Aboard | \n",
629 | " Parents/Children Aboard | \n",
630 | " Fare | \n",
631 | "
\n",
632 | " \n",
633 | " \n",
634 | " \n",
635 | " | 0 | \n",
636 | " 0 | \n",
637 | " 3 | \n",
638 | " Mr. Owen Harris Braund | \n",
639 | " male | \n",
640 | " 22.0 | \n",
641 | " 1 | \n",
642 | " 0 | \n",
643 | " 7.2500 | \n",
644 | "
\n",
645 | " \n",
646 | " | 1 | \n",
647 | " 1 | \n",
648 | " 1 | \n",
649 | " Mrs. John Bradley (Florence Briggs Thayer) Cum... | \n",
650 | " female | \n",
651 | " 38.0 | \n",
652 | " 1 | \n",
653 | " 0 | \n",
654 | " 71.2833 | \n",
655 | "
\n",
656 | " \n",
657 | " | 2 | \n",
658 | " 1 | \n",
659 | " 3 | \n",
660 | " Miss. Laina Heikkinen | \n",
661 | " female | \n",
662 | " 26.0 | \n",
663 | " 0 | \n",
664 | " 0 | \n",
665 | " 7.9250 | \n",
666 | "
\n",
667 | " \n",
668 | " | 3 | \n",
669 | " 1 | \n",
670 | " 1 | \n",
671 | " Mrs. Jacques Heath (Lily May Peel) Futrelle | \n",
672 | " female | \n",
673 | " 35.0 | \n",
674 | " 1 | \n",
675 | " 0 | \n",
676 | " 53.1000 | \n",
677 | "
\n",
678 | " \n",
679 | " | 4 | \n",
680 | " 0 | \n",
681 | " 3 | \n",
682 | " Mr. William Henry Allen | \n",
683 | " male | \n",
684 | " 35.0 | \n",
685 | " 0 | \n",
686 | " 0 | \n",
687 | " 8.0500 | \n",
688 | "
\n",
689 | " \n",
690 | " | ... | \n",
691 | " ... | \n",
692 | " ... | \n",
693 | " ... | \n",
694 | " ... | \n",
695 | " ... | \n",
696 | " ... | \n",
697 | " ... | \n",
698 | " ... | \n",
699 | "
\n",
700 | " \n",
701 | " | 882 | \n",
702 | " 0 | \n",
703 | " 2 | \n",
704 | " Rev. Juozas Montvila | \n",
705 | " male | \n",
706 | " 27.0 | \n",
707 | " 0 | \n",
708 | " 0 | \n",
709 | " 13.0000 | \n",
710 | "
\n",
711 | " \n",
712 | " | 883 | \n",
713 | " 1 | \n",
714 | " 1 | \n",
715 | " Miss. Margaret Edith Graham | \n",
716 | " female | \n",
717 | " 19.0 | \n",
718 | " 0 | \n",
719 | " 0 | \n",
720 | " 30.0000 | \n",
721 | "
\n",
722 | " \n",
723 | " | 884 | \n",
724 | " 0 | \n",
725 | " 3 | \n",
726 | " Miss. Catherine Helen Johnston | \n",
727 | " female | \n",
728 | " 7.0 | \n",
729 | " 1 | \n",
730 | " 2 | \n",
731 | " 23.4500 | \n",
732 | "
\n",
733 | " \n",
734 | " | 885 | \n",
735 | " 1 | \n",
736 | " 1 | \n",
737 | " Mr. Karl Howell Behr | \n",
738 | " male | \n",
739 | " 26.0 | \n",
740 | " 0 | \n",
741 | " 0 | \n",
742 | " 30.0000 | \n",
743 | "
\n",
744 | " \n",
745 | " | 886 | \n",
746 | " 0 | \n",
747 | " 3 | \n",
748 | " Mr. Patrick Dooley | \n",
749 | " male | \n",
750 | " 32.0 | \n",
751 | " 0 | \n",
752 | " 0 | \n",
753 | " 7.7500 | \n",
754 | "
\n",
755 | " \n",
756 | "
\n",
757 | "
887 rows × 8 columns
\n",
758 | "
\n",
828 | "\n",
841 | "
\n",
842 | " \n",
843 | " \n",
844 | " | \n",
845 | " Survived | \n",
846 | " Pclass | \n",
847 | " Name | \n",
848 | " Sex | \n",
849 | " Age | \n",
850 | " Siblings/Spouses Aboard | \n",
851 | " Parents/Children Aboard | \n",
852 | " Fare | \n",
853 | "
\n",
854 | " \n",
855 | " \n",
856 | " \n",
857 | " | 0 | \n",
858 | " 0 | \n",
859 | " 3 | \n",
860 | " Mr. Owen Harris Braund | \n",
861 | " male | \n",
862 | " 22.0 | \n",
863 | " 1 | \n",
864 | " 0 | \n",
865 | " 7.2500 | \n",
866 | "
\n",
867 | " \n",
868 | " | 1 | \n",
869 | " 1 | \n",
870 | " 1 | \n",
871 | " Mrs. John Bradley (Florence Briggs Thayer) Cum... | \n",
872 | " female | \n",
873 | " 38.0 | \n",
874 | " 1 | \n",
875 | " 0 | \n",
876 | " 71.2833 | \n",
877 | "
\n",
878 | " \n",
879 | " | 2 | \n",
880 | " 1 | \n",
881 | " 3 | \n",
882 | " Miss. Laina Heikkinen | \n",
883 | " female | \n",
884 | " 26.0 | \n",
885 | " 0 | \n",
886 | " 0 | \n",
887 | " 7.9250 | \n",
888 | "
\n",
889 | " \n",
890 | " | 3 | \n",
891 | " 1 | \n",
892 | " 1 | \n",
893 | " Mrs. Jacques Heath (Lily May Peel) Futrelle | \n",
894 | " female | \n",
895 | " 35.0 | \n",
896 | " 1 | \n",
897 | " 0 | \n",
898 | " 53.1000 | \n",
899 | "
\n",
900 | " \n",
901 | " | 4 | \n",
902 | " 0 | \n",
903 | " 3 | \n",
904 | " Mr. William Henry Allen | \n",
905 | " male | \n",
906 | " 35.0 | \n",
907 | " 0 | \n",
908 | " 0 | \n",
909 | " 8.0500 | \n",
910 | "
\n",
911 | " \n",
912 | " | ... | \n",
913 | " ... | \n",
914 | " ... | \n",
915 | " ... | \n",
916 | " ... | \n",
917 | " ... | \n",
918 | " ... | \n",
919 | " ... | \n",
920 | " ... | \n",
921 | "
\n",
922 | " \n",
923 | " | 882 | \n",
924 | " 0 | \n",
925 | " 2 | \n",
926 | " Rev. Juozas Montvila | \n",
927 | " male | \n",
928 | " 27.0 | \n",
929 | " 0 | \n",
930 | " 0 | \n",
931 | " 13.0000 | \n",
932 | "
\n",
933 | " \n",
934 | " | 883 | \n",
935 | " 1 | \n",
936 | " 1 | \n",
937 | " Miss. Margaret Edith Graham | \n",
938 | " female | \n",
939 | " 19.0 | \n",
940 | " 0 | \n",
941 | " 0 | \n",
942 | " 30.0000 | \n",
943 | "
\n",
944 | " \n",
945 | " | 884 | \n",
946 | " 0 | \n",
947 | " 3 | \n",
948 | " Miss. Catherine Helen Johnston | \n",
949 | " female | \n",
950 | " 7.0 | \n",
951 | " 1 | \n",
952 | " 2 | \n",
953 | " 23.4500 | \n",
954 | "
\n",
955 | " \n",
956 | " | 885 | \n",
957 | " 1 | \n",
958 | " 1 | \n",
959 | " Mr. Karl Howell Behr | \n",
960 | " male | \n",
961 | " 26.0 | \n",
962 | " 0 | \n",
963 | " 0 | \n",
964 | " 30.0000 | \n",
965 | "
\n",
966 | " \n",
967 | " | 886 | \n",
968 | " 0 | \n",
969 | " 3 | \n",
970 | " Mr. Patrick Dooley | \n",
971 | " male | \n",
972 | " 32.0 | \n",
973 | " 0 | \n",
974 | " 0 | \n",
975 | " 7.7500 | \n",
976 | "
\n",
977 | " \n",
978 | "
\n",
979 | "
887 rows × 8 columns
\n",
980 | "
\n",
1051 | "\n",
1064 | "
\n",
1065 | " \n",
1066 | " \n",
1067 | " | \n",
1068 | " Survived | \n",
1069 | " Pclass | \n",
1070 | " Name | \n",
1071 | " Sex | \n",
1072 | " Age | \n",
1073 | " Siblings/Spouses Aboard | \n",
1074 | " Parents/Children Aboard | \n",
1075 | " Fare | \n",
1076 | "
\n",
1077 | " \n",
1078 | " \n",
1079 | " \n",
1080 | " | 0 | \n",
1081 | " 0 | \n",
1082 | " 3 | \n",
1083 | " Mr. Owen Harris Braund | \n",
1084 | " male | \n",
1085 | " 22.0 | \n",
1086 | " 1 | \n",
1087 | " 0 | \n",
1088 | " 7.2500 | \n",
1089 | "
\n",
1090 | " \n",
1091 | " | 1 | \n",
1092 | " 1 | \n",
1093 | " 1 | \n",
1094 | " Mrs. John Bradley (Florence Briggs Thayer) Cum... | \n",
1095 | " female | \n",
1096 | " 38.0 | \n",
1097 | " 1 | \n",
1098 | " 0 | \n",
1099 | " 71.2833 | \n",
1100 | "
\n",
1101 | " \n",
1102 | " | 2 | \n",
1103 | " 1 | \n",
1104 | " 3 | \n",
1105 | " Miss. Laina Heikkinen | \n",
1106 | " female | \n",
1107 | " 26.0 | \n",
1108 | " 0 | \n",
1109 | " 0 | \n",
1110 | " 7.9250 | \n",
1111 | "
\n",
1112 | " \n",
1113 | " | 3 | \n",
1114 | " 1 | \n",
1115 | " 1 | \n",
1116 | " Mrs. Jacques Heath (Lily May Peel) Futrelle | \n",
1117 | " female | \n",
1118 | " 35.0 | \n",
1119 | " 1 | \n",
1120 | " 0 | \n",
1121 | " 53.1000 | \n",
1122 | "
\n",
1123 | " \n",
1124 | " | 4 | \n",
1125 | " 0 | \n",
1126 | " 3 | \n",
1127 | " Mr. William Henry Allen | \n",
1128 | " male | \n",
1129 | " 35.0 | \n",
1130 | " 0 | \n",
1131 | " 0 | \n",
1132 | " 8.0500 | \n",
1133 | "
\n",
1134 | " \n",
1135 | " | ... | \n",
1136 | " ... | \n",
1137 | " ... | \n",
1138 | " ... | \n",
1139 | " ... | \n",
1140 | " ... | \n",
1141 | " ... | \n",
1142 | " ... | \n",
1143 | " ... | \n",
1144 | "
\n",
1145 | " \n",
1146 | " | 882 | \n",
1147 | " 0 | \n",
1148 | " 2 | \n",
1149 | " Rev. Juozas Montvila | \n",
1150 | " male | \n",
1151 | " 27.0 | \n",
1152 | " 0 | \n",
1153 | " 0 | \n",
1154 | " 13.0000 | \n",
1155 | "
\n",
1156 | " \n",
1157 | " | 883 | \n",
1158 | " 1 | \n",
1159 | " 1 | \n",
1160 | " Miss. Margaret Edith Graham | \n",
1161 | " female | \n",
1162 | " 19.0 | \n",
1163 | " 0 | \n",
1164 | " 0 | \n",
1165 | " 30.0000 | \n",
1166 | "
\n",
1167 | " \n",
1168 | " | 884 | \n",
1169 | " 0 | \n",
1170 | " 3 | \n",
1171 | " Miss. Catherine Helen Johnston | \n",
1172 | " female | \n",
1173 | " 7.0 | \n",
1174 | " 1 | \n",
1175 | " 2 | \n",
1176 | " 23.4500 | \n",
1177 | "
\n",
1178 | " \n",
1179 | " | 885 | \n",
1180 | " 1 | \n",
1181 | " 1 | \n",
1182 | " Mr. Karl Howell Behr | \n",
1183 | " male | \n",
1184 | " 26.0 | \n",
1185 | " 0 | \n",
1186 | " 0 | \n",
1187 | " 30.0000 | \n",
1188 | "
\n",
1189 | " \n",
1190 | " | 886 | \n",
1191 | " 0 | \n",
1192 | " 3 | \n",
1193 | " Mr. Patrick Dooley | \n",
1194 | " male | \n",
1195 | " 32.0 | \n",
1196 | " 0 | \n",
1197 | " 0 | \n",
1198 | " 7.7500 | \n",
1199 | "
\n",
1200 | " \n",
1201 | "
\n",
1202 | "
887 rows × 8 columns
\n",
1203 | "
\n",
1274 | "\n",
1287 | "
\n",
1288 | " \n",
1289 | " \n",
1290 | " | \n",
1291 | " Survived | \n",
1292 | " Pclass | \n",
1293 | " Name | \n",
1294 | " Sex | \n",
1295 | " Age | \n",
1296 | " Siblings/Spouses Aboard | \n",
1297 | " Parents/Children Aboard | \n",
1298 | " Fare | \n",
1299 | "
\n",
1300 | " \n",
1301 | " \n",
1302 | " \n",
1303 | " | 0 | \n",
1304 | " 0 | \n",
1305 | " 3 | \n",
1306 | " Mr. Owen Harris Braund | \n",
1307 | " male | \n",
1308 | " 22.0 | \n",
1309 | " 1 | \n",
1310 | " 0 | \n",
1311 | " 7.2500 | \n",
1312 | "
\n",
1313 | " \n",
1314 | " | 1 | \n",
1315 | " 1 | \n",
1316 | " 1 | \n",
1317 | " Mrs. John Bradley (Florence Briggs Thayer) Cum... | \n",
1318 | " female | \n",
1319 | " 38.0 | \n",
1320 | " 1 | \n",
1321 | " 0 | \n",
1322 | " 71.2833 | \n",
1323 | "
\n",
1324 | " \n",
1325 | " | 2 | \n",
1326 | " 1 | \n",
1327 | " 3 | \n",
1328 | " Miss. Laina Heikkinen | \n",
1329 | " female | \n",
1330 | " 26.0 | \n",
1331 | " 0 | \n",
1332 | " 0 | \n",
1333 | " 7.9250 | \n",
1334 | "
\n",
1335 | " \n",
1336 | " | 3 | \n",
1337 | " 1 | \n",
1338 | " 1 | \n",
1339 | " Mrs. Jacques Heath (Lily May Peel) Futrelle | \n",
1340 | " female | \n",
1341 | " 35.0 | \n",
1342 | " 1 | \n",
1343 | " 0 | \n",
1344 | " 53.1000 | \n",
1345 | "
\n",
1346 | " \n",
1347 | " | 4 | \n",
1348 | " 0 | \n",
1349 | " 3 | \n",
1350 | " Mr. William Henry Allen | \n",
1351 | " male | \n",
1352 | " 35.0 | \n",
1353 | " 0 | \n",
1354 | " 0 | \n",
1355 | " 8.0500 | \n",
1356 | "
\n",
1357 | " \n",
1358 | " | ... | \n",
1359 | " ... | \n",
1360 | " ... | \n",
1361 | " ... | \n",
1362 | " ... | \n",
1363 | " ... | \n",
1364 | " ... | \n",
1365 | " ... | \n",
1366 | " ... | \n",
1367 | "
\n",
1368 | " \n",
1369 | " | 882 | \n",
1370 | " 0 | \n",
1371 | " 2 | \n",
1372 | " Rev. Juozas Montvila | \n",
1373 | " male | \n",
1374 | " 27.0 | \n",
1375 | " 0 | \n",
1376 | " 0 | \n",
1377 | " 13.0000 | \n",
1378 | "
\n",
1379 | " \n",
1380 | " | 883 | \n",
1381 | " 1 | \n",
1382 | " 1 | \n",
1383 | " Miss. Margaret Edith Graham | \n",
1384 | " female | \n",
1385 | " 19.0 | \n",
1386 | " 0 | \n",
1387 | " 0 | \n",
1388 | " 30.0000 | \n",
1389 | "
\n",
1390 | " \n",
1391 | " | 884 | \n",
1392 | " 0 | \n",
1393 | " 3 | \n",
1394 | " Miss. Catherine Helen Johnston | \n",
1395 | " female | \n",
1396 | " 7.0 | \n",
1397 | " 1 | \n",
1398 | " 2 | \n",
1399 | " 23.4500 | \n",
1400 | "
\n",
1401 | " \n",
1402 | " | 885 | \n",
1403 | " 1 | \n",
1404 | " 1 | \n",
1405 | " Mr. Karl Howell Behr | \n",
1406 | " male | \n",
1407 | " 26.0 | \n",
1408 | " 0 | \n",
1409 | " 0 | \n",
1410 | " 30.0000 | \n",
1411 | "
\n",
1412 | " \n",
1413 | " | 886 | \n",
1414 | " 0 | \n",
1415 | " 3 | \n",
1416 | " Mr. Patrick Dooley | \n",
1417 | " male | \n",
1418 | " 32.0 | \n",
1419 | " 0 | \n",
1420 | " 0 | \n",
1421 | " 7.7500 | \n",
1422 | "
\n",
1423 | " \n",
1424 | "
\n",
1425 | "
887 rows × 8 columns
\n",
1426 | "