├── MovieLens
    ├── .gitignore
    ├── extra-imdb-info.ipynb
    └── data-processing.ipynb
├── README.md
├── WorldCup
    └── download.ipynb
└── .gitignore


/MovieLens/.gitignore:
--------------------------------------------------------------------------------
1 | # files
2 | *.zip
3 | *.csv
4 | *.txt


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # neotwork-datasets
2 | Take network datasets and feed them to neo4j
3 | 


--------------------------------------------------------------------------------
/WorldCup/download.ipynb:
--------------------------------------------------------------------------------
 1 | {
 2 |  "cells": [
 3 |   {
 4 |    "cell_type": "code",
 5 |    "execution_count": null,
 6 |    "metadata": {},
 7 |    "outputs": [],
 8 |    "source": []
 9 |   }
10 |  ],
11 |  "metadata": {
12 |   "kernelspec": {
13 |    "display_name": "Python 3",
14 |    "language": "python",
15 |    "name": "python3"
16 |   },
17 |   "language_info": {
18 |    "codemirror_mode": {
19 |     "name": "ipython",
20 |     "version": 3
21 |    },
22 |    "file_extension": ".py",
23 |    "mimetype": "text/x-python",
24 |    "name": "python",
25 |    "nbconvert_exporter": "python",
26 |    "pygments_lexer": "ipython3",
27 |    "version": "3.6.4"
28 |   }
29 |  },
30 |  "nbformat": 4,
31 |  "nbformat_minor": 2
32 | }
33 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | 
 2 | # Created by https://www.gitignore.io/api/macos,windows,jupyternotebook
 3 | 
 4 | ### JupyterNotebook ###
 5 | .ipynb_checkpoints
 6 | */.ipynb_checkpoints/*
 7 | 
 8 | # Remove previous ipynb_checkpoints
 9 | #   git rm -r .ipynb_checkpoints/
10 | #
11 | ### macOS ###
12 | *.DS_Store
13 | .AppleDouble
14 | .LSOverride
15 | 
16 | # Icon must end with two \r
17 | Icon
18 | 
19 | # Thumbnails
20 | ._*
21 | 
22 | # Files that might appear in the root of a volume
23 | .DocumentRevisions-V100
24 | .fseventsd
25 | .Spotlight-V100
26 | .TemporaryItems
27 | .Trashes
28 | .VolumeIcon.icns
29 | .com.apple.timemachine.donotpresent
30 | 
31 | # Directories potentially created on remote AFP share
32 | .AppleDB
33 | .AppleDesktop
34 | Network Trash Folder
35 | Temporary Items
36 | .apdisk
37 | 
38 | ### Windows ###
39 | # Windows thumbnail cache files
40 | Thumbs.db
41 | ehthumbs.db
42 | ehthumbs_vista.db
43 | 
44 | # Folder config file
45 | Desktop.ini
46 | 
47 | # Recycle Bin used on file shares
48 | $RECYCLE.BIN/
49 | 
50 | # Windows Installer files
51 | *.cab
52 | *.msi
53 | *.msm
54 | *.msp
55 | 
56 | # Windows shortcuts
57 | *.lnk
58 | 
59 | 
60 | # End of https://www.gitignore.io/api/macos,windows,jupyternotebook
61 | 
62 | # files
63 | *.zip
64 | *.csv
65 | 


--------------------------------------------------------------------------------
/MovieLens/extra-imdb-info.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 3,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "from imdb import IMDb"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "metadata": {},
 17 |    "outputs": [
 18 |     {
 19 |      "data": {
 20 |       "text/html": [
 21 |        "<div>\n",
 22 |        "<style scoped>\n",
 23 |        "    .dataframe tbody tr th:only-of-type {\n",
 24 |        "        vertical-align: middle;\n",
 25 |        "    }\n",
 26 |        "\n",
 27 |        "    .dataframe tbody tr th {\n",
 28 |        "        vertical-align: top;\n",
 29 |        "    }\n",
 30 |        "\n",
 31 |        "    .dataframe thead th {\n",
 32 |        "        text-align: right;\n",
 33 |        "    }\n",
 34 |        "</style>\n",
 35 |        "<table border=\"1\" class=\"dataframe\">\n",
 36 |        "  <thead>\n",
 37 |        "    <tr style=\"text-align: right;\">\n",
 38 |        "      <th></th>\n",
 39 |        "      <th>title</th>\n",
 40 |        "      <th>imdbId</th>\n",
 41 |        "      <th>tmdbId</th>\n",
 42 |        "      <th>year</th>\n",
 43 |        "    </tr>\n",
 44 |        "    <tr>\n",
 45 |        "      <th>movieId</th>\n",
 46 |        "      <th></th>\n",
 47 |        "      <th></th>\n",
 48 |        "      <th></th>\n",
 49 |        "      <th></th>\n",
 50 |        "    </tr>\n",
 51 |        "  </thead>\n",
 52 |        "  <tbody>\n",
 53 |        "    <tr>\n",
 54 |        "      <th>1</th>\n",
 55 |        "      <td>Toy Story</td>\n",
 56 |        "      <td>114709</td>\n",
 57 |        "      <td>862</td>\n",
 58 |        "      <td>1995</td>\n",
 59 |        "    </tr>\n",
 60 |        "    <tr>\n",
 61 |        "      <th>2</th>\n",
 62 |        "      <td>Jumanji</td>\n",
 63 |        "      <td>113497</td>\n",
 64 |        "      <td>8844</td>\n",
 65 |        "      <td>1995</td>\n",
 66 |        "    </tr>\n",
 67 |        "    <tr>\n",
 68 |        "      <th>3</th>\n",
 69 |        "      <td>Grumpier Old Men</td>\n",
 70 |        "      <td>113228</td>\n",
 71 |        "      <td>15602</td>\n",
 72 |        "      <td>1995</td>\n",
 73 |        "    </tr>\n",
 74 |        "    <tr>\n",
 75 |        "      <th>4</th>\n",
 76 |        "      <td>Waiting to Exhale</td>\n",
 77 |        "      <td>114885</td>\n",
 78 |        "      <td>31357</td>\n",
 79 |        "      <td>1995</td>\n",
 80 |        "    </tr>\n",
 81 |        "    <tr>\n",
 82 |        "      <th>5</th>\n",
 83 |        "      <td>Father of the Bride Part II</td>\n",
 84 |        "      <td>113041</td>\n",
 85 |        "      <td>11862</td>\n",
 86 |        "      <td>1995</td>\n",
 87 |        "    </tr>\n",
 88 |        "  </tbody>\n",
 89 |        "</table>\n",
 90 |        "</div>"
 91 |       ],
 92 |       "text/plain": [
 93 |        "                               title  imdbId  tmdbId  year\n",
 94 |        "movieId                                                   \n",
 95 |        "1                          Toy Story  114709     862  1995\n",
 96 |        "2                            Jumanji  113497    8844  1995\n",
 97 |        "3                   Grumpier Old Men  113228   15602  1995\n",
 98 |        "4                  Waiting to Exhale  114885   31357  1995\n",
 99 |        "5        Father of the Bride Part II  113041   11862  1995"
100 |       ]
101 |      },
102 |      "execution_count": 2,
103 |      "metadata": {},
104 |      "output_type": "execute_result"
105 |     }
106 |    ],
107 |    "source": [
108 |     "movies = pd.read_csv(\"movies.clean.csv\", index_col=0)\n",
109 |     "movies.head()"
110 |    ]
111 |   },
112 |   {
113 |    "cell_type": "code",
114 |    "execution_count": 5,
115 |    "metadata": {},
116 |    "outputs": [],
117 |    "source": [
118 |     "ia = IMDb()"
119 |    ]
120 |   },
121 |   {
122 |    "cell_type": "code",
123 |    "execution_count": 20,
124 |    "metadata": {},
125 |    "outputs": [
126 |     {
127 |      "data": {
128 |       "text/plain": [
129 |        "['cast',\n",
130 |        " 'genres',\n",
131 |        " 'runtimes',\n",
132 |        " 'countries',\n",
133 |        " 'country codes',\n",
134 |        " 'language codes',\n",
135 |        " 'color info',\n",
136 |        " 'aspect ratio',\n",
137 |        " 'sound mix',\n",
138 |        " 'certificates',\n",
139 |        " 'original air date',\n",
140 |        " 'rating',\n",
141 |        " 'votes',\n",
142 |        " 'cover url',\n",
143 |        " 'plot outline',\n",
144 |        " 'languages',\n",
145 |        " 'title',\n",
146 |        " 'year',\n",
147 |        " 'kind',\n",
148 |        " 'directors',\n",
149 |        " 'writers',\n",
150 |        " 'producers',\n",
151 |        " 'composers',\n",
152 |        " 'editors',\n",
153 |        " 'editorial department',\n",
154 |        " 'casting directors',\n",
155 |        " 'art directors',\n",
156 |        " 'production managers ',\n",
157 |        " 'art department',\n",
158 |        " 'sound department',\n",
159 |        " 'visual effects',\n",
160 |        " 'camera department',\n",
161 |        " 'animation department',\n",
162 |        " 'casting department',\n",
163 |        " 'music department',\n",
164 |        " 'miscellaneous',\n",
165 |        " 'akas',\n",
166 |        " 'writer',\n",
167 |        " 'director',\n",
168 |        " 'top 250 rank',\n",
169 |        " 'plot',\n",
170 |        " 'synopsis',\n",
171 |        " 'canonical title',\n",
172 |        " 'long imdb title',\n",
173 |        " 'long imdb canonical title',\n",
174 |        " 'smart canonical title',\n",
175 |        " 'smart long imdb canonical title',\n",
176 |        " 'full-size cover url']"
177 |       ]
178 |      },
179 |      "execution_count": 20,
180 |      "metadata": {},
181 |      "output_type": "execute_result"
182 |     }
183 |    ],
184 |    "source": [
185 |     "movie = ia.get_movie(114709)\n",
186 |     "movie.keys()"
187 |    ]
188 |   },
189 |   {
190 |    "cell_type": "code",
191 |    "execution_count": 19,
192 |    "metadata": {},
193 |    "outputs": [
194 |     {
195 |      "name": "stdout",
196 |      "output_type": "stream",
197 |      "text": [
198 |       "Lasseter, John\n"
199 |      ]
200 |     },
201 |     {
202 |      "data": {
203 |       "text/plain": [
204 |        "['name', 'canonical name', 'long imdb name', 'long imdb canonical name']"
205 |       ]
206 |      },
207 |      "execution_count": 19,
208 |      "metadata": {},
209 |      "output_type": "execute_result"
210 |     }
211 |    ],
212 |    "source": [
213 |     "one_director = movie[\"director\"][0]\n",
214 |     "print(one_director['canonical name'])\n",
215 |     "one_director.keys()"
216 |    ]
217 |   },
218 |   {
219 |    "cell_type": "code",
220 |    "execution_count": null,
221 |    "metadata": {},
222 |    "outputs": [],
223 |    "source": []
224 |   }
225 |  ],
226 |  "metadata": {
227 |   "kernelspec": {
228 |    "display_name": "Python 3",
229 |    "language": "python",
230 |    "name": "python3"
231 |   },
232 |   "language_info": {
233 |    "codemirror_mode": {
234 |     "name": "ipython",
235 |     "version": 3
236 |    },
237 |    "file_extension": ".py",
238 |    "mimetype": "text/x-python",
239 |    "name": "python",
240 |    "nbconvert_exporter": "python",
241 |    "pygments_lexer": "ipython3",
242 |    "version": "3.6.5"
243 |   }
244 |  },
245 |  "nbformat": 4,
246 |  "nbformat_minor": 2
247 | }
248 | 


--------------------------------------------------------------------------------
/MovieLens/data-processing.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 25,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np\n",
 11 |     "import os\n",
 12 |     "import re"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "code",
 17 |    "execution_count": 2,
 18 |    "metadata": {},
 19 |    "outputs": [
 20 |     {
 21 |      "name": "stdout",
 22 |      "output_type": "stream",
 23 |      "text": [
 24 |       "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
 25 |       "                                 Dload  Upload   Total   Spent    Left  Speed\n",
 26 |       "100  896k  100  896k    0     0   593k      0  0:00:01  0:00:01 --:--:--  179k 593k\n"
 27 |      ]
 28 |     }
 29 |    ],
 30 |    "source": [
 31 |     "ml_latest_small = \"ml-latest-small.zip\"\n",
 32 |     "\n",
 33 |     "!curl -o  $ml_latest_small http://files.grouplens.org/datasets/movielens/ml-latest-small.zip"
 34 |    ]
 35 |   },
 36 |   {
 37 |    "cell_type": "code",
 38 |    "execution_count": 4,
 39 |    "metadata": {},
 40 |    "outputs": [],
 41 |    "source": [
 42 |     "import zipfile\n",
 43 |     "with zipfile.ZipFile(ml_latest_small, 'r') as zip_ref:\n",
 44 |     "    zip_ref.extractall(\".\")"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "code",
 49 |    "execution_count": 5,
 50 |    "metadata": {},
 51 |    "outputs": [
 52 |     {
 53 |      "data": {
 54 |       "text/html": [
 55 |        "<div>\n",
 56 |        "<style scoped>\n",
 57 |        "    .dataframe tbody tr th:only-of-type {\n",
 58 |        "        vertical-align: middle;\n",
 59 |        "    }\n",
 60 |        "\n",
 61 |        "    .dataframe tbody tr th {\n",
 62 |        "        vertical-align: top;\n",
 63 |        "    }\n",
 64 |        "\n",
 65 |        "    .dataframe thead th {\n",
 66 |        "        text-align: right;\n",
 67 |        "    }\n",
 68 |        "</style>\n",
 69 |        "<table border=\"1\" class=\"dataframe\">\n",
 70 |        "  <thead>\n",
 71 |        "    <tr style=\"text-align: right;\">\n",
 72 |        "      <th></th>\n",
 73 |        "      <th>title</th>\n",
 74 |        "      <th>genres</th>\n",
 75 |        "      <th>imdbId</th>\n",
 76 |        "      <th>tmdbId</th>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>movieId</th>\n",
 80 |        "      <th></th>\n",
 81 |        "      <th></th>\n",
 82 |        "      <th></th>\n",
 83 |        "      <th></th>\n",
 84 |        "    </tr>\n",
 85 |        "  </thead>\n",
 86 |        "  <tbody>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>1</th>\n",
 89 |        "      <td>Toy Story (1995)</td>\n",
 90 |        "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
 91 |        "      <td>114709</td>\n",
 92 |        "      <td>862</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>2</th>\n",
 96 |        "      <td>Jumanji (1995)</td>\n",
 97 |        "      <td>Adventure|Children|Fantasy</td>\n",
 98 |        "      <td>113497</td>\n",
 99 |        "      <td>8844</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>3</th>\n",
103 |        "      <td>Grumpier Old Men (1995)</td>\n",
104 |        "      <td>Comedy|Romance</td>\n",
105 |        "      <td>113228</td>\n",
106 |        "      <td>15602</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>4</th>\n",
110 |        "      <td>Waiting to Exhale (1995)</td>\n",
111 |        "      <td>Comedy|Drama|Romance</td>\n",
112 |        "      <td>114885</td>\n",
113 |        "      <td>31357</td>\n",
114 |        "    </tr>\n",
115 |        "    <tr>\n",
116 |        "      <th>5</th>\n",
117 |        "      <td>Father of the Bride Part II (1995)</td>\n",
118 |        "      <td>Comedy</td>\n",
119 |        "      <td>113041</td>\n",
120 |        "      <td>11862</td>\n",
121 |        "    </tr>\n",
122 |        "  </tbody>\n",
123 |        "</table>\n",
124 |        "</div>"
125 |       ],
126 |       "text/plain": [
127 |        "                                      title  \\\n",
128 |        "movieId                                       \n",
129 |        "1                          Toy Story (1995)   \n",
130 |        "2                            Jumanji (1995)   \n",
131 |        "3                   Grumpier Old Men (1995)   \n",
132 |        "4                  Waiting to Exhale (1995)   \n",
133 |        "5        Father of the Bride Part II (1995)   \n",
134 |        "\n",
135 |        "                                              genres  imdbId  tmdbId  \n",
136 |        "movieId                                                               \n",
137 |        "1        Adventure|Animation|Children|Comedy|Fantasy  114709     862  \n",
138 |        "2                         Adventure|Children|Fantasy  113497    8844  \n",
139 |        "3                                     Comedy|Romance  113228   15602  \n",
140 |        "4                               Comedy|Drama|Romance  114885   31357  \n",
141 |        "5                                             Comedy  113041   11862  "
142 |       ]
143 |      },
144 |      "execution_count": 5,
145 |      "metadata": {},
146 |      "output_type": "execute_result"
147 |     }
148 |    ],
149 |    "source": [
150 |     "movies = pd.read_csv(\"ml-latest-small/movies.csv\", index_col=0)\n",
151 |     "links = pd.read_csv(\"ml-latest-small/links.csv\", index_col=0)\n",
152 |     "movies = pd.merge(movies, links, left_index=True, right_index=True)\n",
153 |     "movies.tmdbId = movies.tmdbId.apply(lambda v: int(v) if pd.notna(v) else -1)\n",
154 |     "movies.head()"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": 6,
160 |    "metadata": {},
161 |    "outputs": [
162 |     {
163 |      "name": "stdout",
164 |      "output_type": "stream",
165 |      "text": [
166 |       "Witchfinder General (Conquerer Worm, The)\n"
167 |      ]
168 |     },
169 |     {
170 |      "data": {
171 |       "text/html": [
172 |        "<div>\n",
173 |        "<style scoped>\n",
174 |        "    .dataframe tbody tr th:only-of-type {\n",
175 |        "        vertical-align: middle;\n",
176 |        "    }\n",
177 |        "\n",
178 |        "    .dataframe tbody tr th {\n",
179 |        "        vertical-align: top;\n",
180 |        "    }\n",
181 |        "\n",
182 |        "    .dataframe thead th {\n",
183 |        "        text-align: right;\n",
184 |        "    }\n",
185 |        "</style>\n",
186 |        "<table border=\"1\" class=\"dataframe\">\n",
187 |        "  <thead>\n",
188 |        "    <tr style=\"text-align: right;\">\n",
189 |        "      <th></th>\n",
190 |        "      <th>title</th>\n",
191 |        "      <th>genres</th>\n",
192 |        "      <th>imdbId</th>\n",
193 |        "      <th>tmdbId</th>\n",
194 |        "      <th>year</th>\n",
195 |        "    </tr>\n",
196 |        "    <tr>\n",
197 |        "      <th>movieId</th>\n",
198 |        "      <th></th>\n",
199 |        "      <th></th>\n",
200 |        "      <th></th>\n",
201 |        "      <th></th>\n",
202 |        "      <th></th>\n",
203 |        "    </tr>\n",
204 |        "  </thead>\n",
205 |        "  <tbody>\n",
206 |        "    <tr>\n",
207 |        "      <th>1</th>\n",
208 |        "      <td>Toy Story</td>\n",
209 |        "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
210 |        "      <td>114709</td>\n",
211 |        "      <td>862</td>\n",
212 |        "      <td>1995</td>\n",
213 |        "    </tr>\n",
214 |        "    <tr>\n",
215 |        "      <th>2</th>\n",
216 |        "      <td>Jumanji</td>\n",
217 |        "      <td>Adventure|Children|Fantasy</td>\n",
218 |        "      <td>113497</td>\n",
219 |        "      <td>8844</td>\n",
220 |        "      <td>1995</td>\n",
221 |        "    </tr>\n",
222 |        "    <tr>\n",
223 |        "      <th>3</th>\n",
224 |        "      <td>Grumpier Old Men</td>\n",
225 |        "      <td>Comedy|Romance</td>\n",
226 |        "      <td>113228</td>\n",
227 |        "      <td>15602</td>\n",
228 |        "      <td>1995</td>\n",
229 |        "    </tr>\n",
230 |        "    <tr>\n",
231 |        "      <th>4</th>\n",
232 |        "      <td>Waiting to Exhale</td>\n",
233 |        "      <td>Comedy|Drama|Romance</td>\n",
234 |        "      <td>114885</td>\n",
235 |        "      <td>31357</td>\n",
236 |        "      <td>1995</td>\n",
237 |        "    </tr>\n",
238 |        "    <tr>\n",
239 |        "      <th>5</th>\n",
240 |        "      <td>Father of the Bride Part II</td>\n",
241 |        "      <td>Comedy</td>\n",
242 |        "      <td>113041</td>\n",
243 |        "      <td>11862</td>\n",
244 |        "      <td>1995</td>\n",
245 |        "    </tr>\n",
246 |        "  </tbody>\n",
247 |        "</table>\n",
248 |        "</div>"
249 |       ],
250 |       "text/plain": [
251 |        "                               title  \\\n",
252 |        "movieId                                \n",
253 |        "1                          Toy Story   \n",
254 |        "2                            Jumanji   \n",
255 |        "3                   Grumpier Old Men   \n",
256 |        "4                  Waiting to Exhale   \n",
257 |        "5        Father of the Bride Part II   \n",
258 |        "\n",
259 |        "                                              genres  imdbId  tmdbId  year  \n",
260 |        "movieId                                                                     \n",
261 |        "1        Adventure|Animation|Children|Comedy|Fantasy  114709     862  1995  \n",
262 |        "2                         Adventure|Children|Fantasy  113497    8844  1995  \n",
263 |        "3                                     Comedy|Romance  113228   15602  1995  \n",
264 |        "4                               Comedy|Drama|Romance  114885   31357  1995  \n",
265 |        "5                                             Comedy  113041   11862  1995  "
266 |       ]
267 |      },
268 |      "execution_count": 6,
269 |      "metadata": {},
270 |      "output_type": "execute_result"
271 |     }
272 |    ],
273 |    "source": [
274 |     "year = re.compile(\"\\(([0-9]{4})\\)$\")\n",
275 |     "\n",
276 |     "def get_year(date):\n",
277 |     "    match = year.search(date.strip())\n",
278 |     "    if match:\n",
279 |     "        return int(match.group(1))\n",
280 |     "    return -1\n",
281 |     "\n",
282 |     "shave_year = lambda title: title[:-7] if year.search(title) else title\n",
283 |     "\n",
284 |     "print(shave_year(\"Witchfinder General (Conquerer Worm, The) (1968)\"))\n",
285 |     "\n",
286 |     "movies[\"year\"] = movies.title.apply(get_year)\n",
287 |     "movies[\"title\"] = movies.title.apply(shave_year)\n",
288 |     "movies.head()"
289 |    ]
290 |   },
291 |   {
292 |    "cell_type": "code",
293 |    "execution_count": 7,
294 |    "metadata": {},
295 |    "outputs": [
296 |     {
297 |      "data": {
298 |       "text/html": [
299 |        "<div>\n",
300 |        "<style scoped>\n",
301 |        "    .dataframe tbody tr th:only-of-type {\n",
302 |        "        vertical-align: middle;\n",
303 |        "    }\n",
304 |        "\n",
305 |        "    .dataframe tbody tr th {\n",
306 |        "        vertical-align: top;\n",
307 |        "    }\n",
308 |        "\n",
309 |        "    .dataframe thead th {\n",
310 |        "        text-align: right;\n",
311 |        "    }\n",
312 |        "</style>\n",
313 |        "<table border=\"1\" class=\"dataframe\">\n",
314 |        "  <thead>\n",
315 |        "    <tr style=\"text-align: right;\">\n",
316 |        "      <th></th>\n",
317 |        "      <th>title</th>\n",
318 |        "      <th>genres</th>\n",
319 |        "      <th>imdbId</th>\n",
320 |        "      <th>tmdbId</th>\n",
321 |        "      <th>year</th>\n",
322 |        "    </tr>\n",
323 |        "    <tr>\n",
324 |        "      <th>movieId</th>\n",
325 |        "      <th></th>\n",
326 |        "      <th></th>\n",
327 |        "      <th></th>\n",
328 |        "      <th></th>\n",
329 |        "      <th></th>\n",
330 |        "    </tr>\n",
331 |        "  </thead>\n",
332 |        "  <tbody>\n",
333 |        "    <tr>\n",
334 |        "      <th>1</th>\n",
335 |        "      <td>Toy Story</td>\n",
336 |        "      <td>Adventure|Animation|Children|Comedy|Fantasy</td>\n",
337 |        "      <td>114709</td>\n",
338 |        "      <td>862</td>\n",
339 |        "      <td>1995</td>\n",
340 |        "    </tr>\n",
341 |        "    <tr>\n",
342 |        "      <th>2</th>\n",
343 |        "      <td>Jumanji</td>\n",
344 |        "      <td>Adventure|Children|Fantasy</td>\n",
345 |        "      <td>113497</td>\n",
346 |        "      <td>8844</td>\n",
347 |        "      <td>1995</td>\n",
348 |        "    </tr>\n",
349 |        "    <tr>\n",
350 |        "      <th>3</th>\n",
351 |        "      <td>Grumpier Old Men</td>\n",
352 |        "      <td>Comedy|Romance</td>\n",
353 |        "      <td>113228</td>\n",
354 |        "      <td>15602</td>\n",
355 |        "      <td>1995</td>\n",
356 |        "    </tr>\n",
357 |        "    <tr>\n",
358 |        "      <th>4</th>\n",
359 |        "      <td>Waiting to Exhale</td>\n",
360 |        "      <td>Comedy|Drama|Romance</td>\n",
361 |        "      <td>114885</td>\n",
362 |        "      <td>31357</td>\n",
363 |        "      <td>1995</td>\n",
364 |        "    </tr>\n",
365 |        "    <tr>\n",
366 |        "      <th>5</th>\n",
367 |        "      <td>Father of the Bride Part II</td>\n",
368 |        "      <td>Comedy</td>\n",
369 |        "      <td>113041</td>\n",
370 |        "      <td>11862</td>\n",
371 |        "      <td>1995</td>\n",
372 |        "    </tr>\n",
373 |        "  </tbody>\n",
374 |        "</table>\n",
375 |        "</div>"
376 |       ],
377 |       "text/plain": [
378 |        "                               title  \\\n",
379 |        "movieId                                \n",
380 |        "1                          Toy Story   \n",
381 |        "2                            Jumanji   \n",
382 |        "3                   Grumpier Old Men   \n",
383 |        "4                  Waiting to Exhale   \n",
384 |        "5        Father of the Bride Part II   \n",
385 |        "\n",
386 |        "                                              genres  imdbId  tmdbId  year  \n",
387 |        "movieId                                                                     \n",
388 |        "1        Adventure|Animation|Children|Comedy|Fantasy  114709     862  1995  \n",
389 |        "2                         Adventure|Children|Fantasy  113497    8844  1995  \n",
390 |        "3                                     Comedy|Romance  113228   15602  1995  \n",
391 |        "4                               Comedy|Drama|Romance  114885   31357  1995  \n",
392 |        "5                                             Comedy  113041   11862  1995  "
393 |       ]
394 |      },
395 |      "execution_count": 7,
396 |      "metadata": {},
397 |      "output_type": "execute_result"
398 |     }
399 |    ],
400 |    "source": [
401 |     "movies = movies[movies.year!=-1]\n",
402 |     "movies.head()"
403 |    ]
404 |   },
405 |   {
406 |    "cell_type": "code",
407 |    "execution_count": 8,
408 |    "metadata": {},
409 |    "outputs": [],
410 |    "source": [
411 |     "get_genre_set = lambda g: g.split('|')\n",
412 |     "genres = movies.genres.apply(get_genre_set)\n",
413 |     "movies.drop(\"genres\", axis=1, inplace=True)"
414 |    ]
415 |   },
416 |   {
417 |    "cell_type": "code",
418 |    "execution_count": 9,
419 |    "metadata": {},
420 |    "outputs": [
421 |     {
422 |      "data": {
423 |       "text/html": [
424 |        "<div>\n",
425 |        "<style scoped>\n",
426 |        "    .dataframe tbody tr th:only-of-type {\n",
427 |        "        vertical-align: middle;\n",
428 |        "    }\n",
429 |        "\n",
430 |        "    .dataframe tbody tr th {\n",
431 |        "        vertical-align: top;\n",
432 |        "    }\n",
433 |        "\n",
434 |        "    .dataframe thead th {\n",
435 |        "        text-align: right;\n",
436 |        "    }\n",
437 |        "</style>\n",
438 |        "<table border=\"1\" class=\"dataframe\">\n",
439 |        "  <thead>\n",
440 |        "    <tr style=\"text-align: right;\">\n",
441 |        "      <th></th>\n",
442 |        "      <th>title</th>\n",
443 |        "      <th>imdbId</th>\n",
444 |        "      <th>tmdbId</th>\n",
445 |        "      <th>year</th>\n",
446 |        "    </tr>\n",
447 |        "    <tr>\n",
448 |        "      <th>movieId</th>\n",
449 |        "      <th></th>\n",
450 |        "      <th></th>\n",
451 |        "      <th></th>\n",
452 |        "      <th></th>\n",
453 |        "    </tr>\n",
454 |        "  </thead>\n",
455 |        "  <tbody>\n",
456 |        "    <tr>\n",
457 |        "      <th>1</th>\n",
458 |        "      <td>Toy Story</td>\n",
459 |        "      <td>114709</td>\n",
460 |        "      <td>862</td>\n",
461 |        "      <td>1995</td>\n",
462 |        "    </tr>\n",
463 |        "    <tr>\n",
464 |        "      <th>2</th>\n",
465 |        "      <td>Jumanji</td>\n",
466 |        "      <td>113497</td>\n",
467 |        "      <td>8844</td>\n",
468 |        "      <td>1995</td>\n",
469 |        "    </tr>\n",
470 |        "    <tr>\n",
471 |        "      <th>3</th>\n",
472 |        "      <td>Grumpier Old Men</td>\n",
473 |        "      <td>113228</td>\n",
474 |        "      <td>15602</td>\n",
475 |        "      <td>1995</td>\n",
476 |        "    </tr>\n",
477 |        "    <tr>\n",
478 |        "      <th>4</th>\n",
479 |        "      <td>Waiting to Exhale</td>\n",
480 |        "      <td>114885</td>\n",
481 |        "      <td>31357</td>\n",
482 |        "      <td>1995</td>\n",
483 |        "    </tr>\n",
484 |        "    <tr>\n",
485 |        "      <th>5</th>\n",
486 |        "      <td>Father of the Bride Part II</td>\n",
487 |        "      <td>113041</td>\n",
488 |        "      <td>11862</td>\n",
489 |        "      <td>1995</td>\n",
490 |        "    </tr>\n",
491 |        "  </tbody>\n",
492 |        "</table>\n",
493 |        "</div>"
494 |       ],
495 |       "text/plain": [
496 |        "                               title  imdbId  tmdbId  year\n",
497 |        "movieId                                                   \n",
498 |        "1                          Toy Story  114709     862  1995\n",
499 |        "2                            Jumanji  113497    8844  1995\n",
500 |        "3                   Grumpier Old Men  113228   15602  1995\n",
501 |        "4                  Waiting to Exhale  114885   31357  1995\n",
502 |        "5        Father of the Bride Part II  113041   11862  1995"
503 |       ]
504 |      },
505 |      "execution_count": 9,
506 |      "metadata": {},
507 |      "output_type": "execute_result"
508 |     }
509 |    ],
510 |    "source": [
511 |     "movies.to_csv(\"movies.clean.csv\")\n",
512 |     "movies.head()"
513 |    ]
514 |   },
515 |   {
516 |    "cell_type": "code",
517 |    "execution_count": 10,
518 |    "metadata": {},
519 |    "outputs": [
520 |     {
521 |      "data": {
522 |       "text/html": [
523 |        "<div>\n",
524 |        "<style scoped>\n",
525 |        "    .dataframe tbody tr th:only-of-type {\n",
526 |        "        vertical-align: middle;\n",
527 |        "    }\n",
528 |        "\n",
529 |        "    .dataframe tbody tr th {\n",
530 |        "        vertical-align: top;\n",
531 |        "    }\n",
532 |        "\n",
533 |        "    .dataframe thead th {\n",
534 |        "        text-align: right;\n",
535 |        "    }\n",
536 |        "</style>\n",
537 |        "<table border=\"1\" class=\"dataframe\">\n",
538 |        "  <thead>\n",
539 |        "    <tr style=\"text-align: right;\">\n",
540 |        "      <th></th>\n",
541 |        "      <th>genre</th>\n",
542 |        "    </tr>\n",
543 |        "    <tr>\n",
544 |        "      <th>movieId</th>\n",
545 |        "      <th></th>\n",
546 |        "    </tr>\n",
547 |        "  </thead>\n",
548 |        "  <tbody>\n",
549 |        "    <tr>\n",
550 |        "      <th>1</th>\n",
551 |        "      <td>Adventure</td>\n",
552 |        "    </tr>\n",
553 |        "    <tr>\n",
554 |        "      <th>1</th>\n",
555 |        "      <td>Animation</td>\n",
556 |        "    </tr>\n",
557 |        "    <tr>\n",
558 |        "      <th>1</th>\n",
559 |        "      <td>Children</td>\n",
560 |        "    </tr>\n",
561 |        "    <tr>\n",
562 |        "      <th>1</th>\n",
563 |        "      <td>Comedy</td>\n",
564 |        "    </tr>\n",
565 |        "    <tr>\n",
566 |        "      <th>1</th>\n",
567 |        "      <td>Fantasy</td>\n",
568 |        "    </tr>\n",
569 |        "  </tbody>\n",
570 |        "</table>\n",
571 |        "</div>"
572 |       ],
573 |       "text/plain": [
574 |        "             genre\n",
575 |        "movieId           \n",
576 |        "1        Adventure\n",
577 |        "1        Animation\n",
578 |        "1         Children\n",
579 |        "1           Comedy\n",
580 |        "1          Fantasy"
581 |       ]
582 |      },
583 |      "execution_count": 10,
584 |      "metadata": {},
585 |      "output_type": "execute_result"
586 |     }
587 |    ],
588 |    "source": [
589 |     "genres_assignation = []\n",
590 |     "for i, gen in genres.iteritems():\n",
591 |     "    for gnre in gen:\n",
592 |     "        genres_assignation.append([i, gnre])\n",
593 |     "genres_df = pd.DataFrame(genres_assignation, columns=[\"movieId\", \"genre\"]).set_index(\"movieId\")\n",
594 |     "genres_df.to_csv(\"genres.csv\")\n",
595 |     "genres_df.head()"
596 |    ]
597 |   },
598 |   {
599 |    "cell_type": "code",
600 |    "execution_count": 11,
601 |    "metadata": {},
602 |    "outputs": [
603 |     {
604 |      "name": "stdout",
605 |      "output_type": "stream",
606 |      "text": [
607 |       "2007-01-15T16:29:38\n"
608 |      ]
609 |     }
610 |    ],
611 |    "source": [
612 |     "import datetime\n",
613 |     "'2015-06-24T12:50:35.556+0100'\n",
614 |     "def date_ms(timestamp):\n",
615 |     "    return datetime.datetime.fromtimestamp(timestamp).strftime('%Y-%m-%dT%H:%M:%S')"
616 |    ]
617 |   },
618 |   {
619 |    "cell_type": "code",
620 |    "execution_count": 12,
621 |    "metadata": {},
622 |    "outputs": [
623 |     {
624 |      "data": {
625 |       "text/html": [
626 |        "<div>\n",
627 |        "<style scoped>\n",
628 |        "    .dataframe tbody tr th:only-of-type {\n",
629 |        "        vertical-align: middle;\n",
630 |        "    }\n",
631 |        "\n",
632 |        "    .dataframe tbody tr th {\n",
633 |        "        vertical-align: top;\n",
634 |        "    }\n",
635 |        "\n",
636 |        "    .dataframe thead th {\n",
637 |        "        text-align: right;\n",
638 |        "    }\n",
639 |        "</style>\n",
640 |        "<table border=\"1\" class=\"dataframe\">\n",
641 |        "  <thead>\n",
642 |        "    <tr style=\"text-align: right;\">\n",
643 |        "      <th></th>\n",
644 |        "      <th></th>\n",
645 |        "      <th>rating</th>\n",
646 |        "      <th>timestamp</th>\n",
647 |        "      <th>time</th>\n",
648 |        "    </tr>\n",
649 |        "    <tr>\n",
650 |        "      <th>userId</th>\n",
651 |        "      <th>movieId</th>\n",
652 |        "      <th></th>\n",
653 |        "      <th></th>\n",
654 |        "      <th></th>\n",
655 |        "    </tr>\n",
656 |        "  </thead>\n",
657 |        "  <tbody>\n",
658 |        "    <tr>\n",
659 |        "      <th rowspan=\"10\" valign=\"top\">1</th>\n",
660 |        "      <th>31</th>\n",
661 |        "      <td>2.5</td>\n",
662 |        "      <td>1260759144</td>\n",
663 |        "      <td>2009-12-14T02:52:24</td>\n",
664 |        "    </tr>\n",
665 |        "    <tr>\n",
666 |        "      <th>1029</th>\n",
667 |        "      <td>3.0</td>\n",
668 |        "      <td>1260759179</td>\n",
669 |        "      <td>2009-12-14T02:52:59</td>\n",
670 |        "    </tr>\n",
671 |        "    <tr>\n",
672 |        "      <th>1061</th>\n",
673 |        "      <td>3.0</td>\n",
674 |        "      <td>1260759182</td>\n",
675 |        "      <td>2009-12-14T02:53:02</td>\n",
676 |        "    </tr>\n",
677 |        "    <tr>\n",
678 |        "      <th>1129</th>\n",
679 |        "      <td>2.0</td>\n",
680 |        "      <td>1260759185</td>\n",
681 |        "      <td>2009-12-14T02:53:05</td>\n",
682 |        "    </tr>\n",
683 |        "    <tr>\n",
684 |        "      <th>1172</th>\n",
685 |        "      <td>4.0</td>\n",
686 |        "      <td>1260759205</td>\n",
687 |        "      <td>2009-12-14T02:53:25</td>\n",
688 |        "    </tr>\n",
689 |        "    <tr>\n",
690 |        "      <th>1263</th>\n",
691 |        "      <td>2.0</td>\n",
692 |        "      <td>1260759151</td>\n",
693 |        "      <td>2009-12-14T02:52:31</td>\n",
694 |        "    </tr>\n",
695 |        "    <tr>\n",
696 |        "      <th>1287</th>\n",
697 |        "      <td>2.0</td>\n",
698 |        "      <td>1260759187</td>\n",
699 |        "      <td>2009-12-14T02:53:07</td>\n",
700 |        "    </tr>\n",
701 |        "    <tr>\n",
702 |        "      <th>1293</th>\n",
703 |        "      <td>2.0</td>\n",
704 |        "      <td>1260759148</td>\n",
705 |        "      <td>2009-12-14T02:52:28</td>\n",
706 |        "    </tr>\n",
707 |        "    <tr>\n",
708 |        "      <th>1339</th>\n",
709 |        "      <td>3.5</td>\n",
710 |        "      <td>1260759125</td>\n",
711 |        "      <td>2009-12-14T02:52:05</td>\n",
712 |        "    </tr>\n",
713 |        "    <tr>\n",
714 |        "      <th>1343</th>\n",
715 |        "      <td>2.0</td>\n",
716 |        "      <td>1260759131</td>\n",
717 |        "      <td>2009-12-14T02:52:11</td>\n",
718 |        "    </tr>\n",
719 |        "  </tbody>\n",
720 |        "</table>\n",
721 |        "</div>"
722 |       ],
723 |       "text/plain": [
724 |        "                rating   timestamp                 time\n",
725 |        "userId movieId                                         \n",
726 |        "1      31          2.5  1260759144  2009-12-14T02:52:24\n",
727 |        "       1029        3.0  1260759179  2009-12-14T02:52:59\n",
728 |        "       1061        3.0  1260759182  2009-12-14T02:53:02\n",
729 |        "       1129        2.0  1260759185  2009-12-14T02:53:05\n",
730 |        "       1172        4.0  1260759205  2009-12-14T02:53:25\n",
731 |        "       1263        2.0  1260759151  2009-12-14T02:52:31\n",
732 |        "       1287        2.0  1260759187  2009-12-14T02:53:07\n",
733 |        "       1293        2.0  1260759148  2009-12-14T02:52:28\n",
734 |        "       1339        3.5  1260759125  2009-12-14T02:52:05\n",
735 |        "       1343        2.0  1260759131  2009-12-14T02:52:11"
736 |       ]
737 |      },
738 |      "execution_count": 12,
739 |      "metadata": {},
740 |      "output_type": "execute_result"
741 |     }
742 |    ],
743 |    "source": [
744 |     "ratings = pd.read_csv(\"ml-latest-small/ratings.csv\", index_col=[0,1])\n",
745 |     "ratings[\"time\"] = ratings.timestamp.apply(date_ms)\n",
746 |     "ratings.to_csv(\"ratings.csv\")\n",
747 |     "ratings.head(10) "
748 |    ]
749 |   },
750 |   {
751 |    "cell_type": "code",
752 |    "execution_count": 39,
753 |    "metadata": {},
754 |    "outputs": [
755 |     {
756 |      "data": {
757 |       "text/html": [
758 |        "<div>\n",
759 |        "<style scoped>\n",
760 |        "    .dataframe tbody tr th:only-of-type {\n",
761 |        "        vertical-align: middle;\n",
762 |        "    }\n",
763 |        "\n",
764 |        "    .dataframe tbody tr th {\n",
765 |        "        vertical-align: top;\n",
766 |        "    }\n",
767 |        "\n",
768 |        "    .dataframe thead th {\n",
769 |        "        text-align: right;\n",
770 |        "    }\n",
771 |        "</style>\n",
772 |        "<table border=\"1\" class=\"dataframe\">\n",
773 |        "  <thead>\n",
774 |        "    <tr style=\"text-align: right;\">\n",
775 |        "      <th></th>\n",
776 |        "      <th></th>\n",
777 |        "      <th>tag</th>\n",
778 |        "      <th>timestamp</th>\n",
779 |        "      <th>time</th>\n",
780 |        "    </tr>\n",
781 |        "    <tr>\n",
782 |        "      <th>userId</th>\n",
783 |        "      <th>movieId</th>\n",
784 |        "      <th></th>\n",
785 |        "      <th></th>\n",
786 |        "      <th></th>\n",
787 |        "    </tr>\n",
788 |        "  </thead>\n",
789 |        "  <tbody>\n",
790 |        "    <tr>\n",
791 |        "      <th rowspan=\"5\" valign=\"top\">15</th>\n",
792 |        "      <th>339</th>\n",
793 |        "      <td>sandra 'boring' bullock</td>\n",
794 |        "      <td>1138537770</td>\n",
795 |        "      <td>2006-01-29T12:29:30</td>\n",
796 |        "    </tr>\n",
797 |        "    <tr>\n",
798 |        "      <th>1955</th>\n",
799 |        "      <td>dentist</td>\n",
800 |        "      <td>1193435061</td>\n",
801 |        "      <td>2007-10-26T22:44:21</td>\n",
802 |        "    </tr>\n",
803 |        "    <tr>\n",
804 |        "      <th>7478</th>\n",
805 |        "      <td>Cambodia</td>\n",
806 |        "      <td>1170560997</td>\n",
807 |        "      <td>2007-02-04T03:49:57</td>\n",
808 |        "    </tr>\n",
809 |        "    <tr>\n",
810 |        "      <th>32892</th>\n",
811 |        "      <td>Russian</td>\n",
812 |        "      <td>1170626366</td>\n",
813 |        "      <td>2007-02-04T21:59:26</td>\n",
814 |        "    </tr>\n",
815 |        "    <tr>\n",
816 |        "      <th>34162</th>\n",
817 |        "      <td>forgettable</td>\n",
818 |        "      <td>1141391765</td>\n",
819 |        "      <td>2006-03-03T13:16:05</td>\n",
820 |        "    </tr>\n",
821 |        "  </tbody>\n",
822 |        "</table>\n",
823 |        "</div>"
824 |       ],
825 |       "text/plain": [
826 |        "                                    tag   timestamp                 time\n",
827 |        "userId movieId                                                          \n",
828 |        "15     339      sandra 'boring' bullock  1138537770  2006-01-29T12:29:30\n",
829 |        "       1955                     dentist  1193435061  2007-10-26T22:44:21\n",
830 |        "       7478                    Cambodia  1170560997  2007-02-04T03:49:57\n",
831 |        "       32892                    Russian  1170626366  2007-02-04T21:59:26\n",
832 |        "       34162                forgettable  1141391765  2006-03-03T13:16:05"
833 |       ]
834 |      },
835 |      "execution_count": 39,
836 |      "metadata": {},
837 |      "output_type": "execute_result"
838 |     }
839 |    ],
840 |    "source": [
841 |     "tags = pd.read_csv(\"ml-latest-small/tags.csv\", index_col=[0,1])\n",
842 |     "tags[\"time\"] = tags.timestamp.apply(date_ms)\n",
843 |     "tags.to_csv(\"tags.csv\")\n",
844 |     "tags.head()"
845 |    ]
846 |   },
847 |   {
848 |    "cell_type": "code",
849 |    "execution_count": 40,
850 |    "metadata": {},
851 |    "outputs": [
852 |     {
853 |      "data": {
854 |       "text/html": [
855 |        "<div>\n",
856 |        "<style scoped>\n",
857 |        "    .dataframe tbody tr th:only-of-type {\n",
858 |        "        vertical-align: middle;\n",
859 |        "    }\n",
860 |        "\n",
861 |        "    .dataframe tbody tr th {\n",
862 |        "        vertical-align: top;\n",
863 |        "    }\n",
864 |        "\n",
865 |        "    .dataframe thead th {\n",
866 |        "        text-align: right;\n",
867 |        "    }\n",
868 |        "</style>\n",
869 |        "<table border=\"1\" class=\"dataframe\">\n",
870 |        "  <thead>\n",
871 |        "    <tr style=\"text-align: right;\">\n",
872 |        "      <th></th>\n",
873 |        "      <th>userId</th>\n",
874 |        "    </tr>\n",
875 |        "  </thead>\n",
876 |        "  <tbody>\n",
877 |        "    <tr>\n",
878 |        "      <th>666</th>\n",
879 |        "      <td>667</td>\n",
880 |        "    </tr>\n",
881 |        "    <tr>\n",
882 |        "      <th>667</th>\n",
883 |        "      <td>668</td>\n",
884 |        "    </tr>\n",
885 |        "    <tr>\n",
886 |        "      <th>668</th>\n",
887 |        "      <td>669</td>\n",
888 |        "    </tr>\n",
889 |        "    <tr>\n",
890 |        "      <th>669</th>\n",
891 |        "      <td>670</td>\n",
892 |        "    </tr>\n",
893 |        "    <tr>\n",
894 |        "      <th>670</th>\n",
895 |        "      <td>671</td>\n",
896 |        "    </tr>\n",
897 |        "  </tbody>\n",
898 |        "</table>\n",
899 |        "</div>"
900 |       ],
901 |       "text/plain": [
902 |        "     userId\n",
903 |        "666     667\n",
904 |        "667     668\n",
905 |        "668     669\n",
906 |        "669     670\n",
907 |        "670     671"
908 |       ]
909 |      },
910 |      "execution_count": 40,
911 |      "metadata": {},
912 |      "output_type": "execute_result"
913 |     }
914 |    ],
915 |    "source": [
916 |     "users = np.unique(np.concatenate(\n",
917 |     "    (ratings.index.levels[0].values , tags.index.levels[0].values)))\n",
918 |     "\n",
919 |     "users_df = pd.DataFrame({'userId':users})\n",
920 |     "users_df.to_csv(\"users.csv\")\n",
921 |     "users_df.tail()"
922 |    ]
923 |   },
924 |   {
925 |    "cell_type": "code",
926 |    "execution_count": null,
927 |    "metadata": {},
928 |    "outputs": [],
929 |    "source": []
930 |   }
931 |  ],
932 |  "metadata": {
933 |   "kernelspec": {
934 |    "display_name": "Python 3",
935 |    "language": "python",
936 |    "name": "python3"
937 |   },
938 |   "language_info": {
939 |    "codemirror_mode": {
940 |     "name": "ipython",
941 |     "version": 3
942 |    },
943 |    "file_extension": ".py",
944 |    "mimetype": "text/x-python",
945 |    "name": "python",
946 |    "nbconvert_exporter": "python",
947 |    "pygments_lexer": "ipython3",
948 |    "version": "3.6.5"
949 |   }
950 |  },
951 |  "nbformat": 4,
952 |  "nbformat_minor": 2
953 | }
954 | 


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