├── README.md
├── Popular_Baby_Names.sql
├── .ipynb_checkpoints
    └── Data-Splitter-checkpoint.ipynb
└── Data-Splitter.ipynb


/README.md:
--------------------------------------------------------------------------------
1 | # Data-Splitter


--------------------------------------------------------------------------------
/Popular_Baby_Names.sql:
--------------------------------------------------------------------------------
1 | create database Popular_Baby_Names
2 | 
3 | use Popular_Baby_Names
4 | 
5 | 
6 | select * from Popular_Baby_Names


--------------------------------------------------------------------------------
/.ipynb_checkpoints/Data-Splitter-checkpoint.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 15,
  6 |    "id": "6463840f",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd \n",
 11 |     "import pyodbc\n",
 12 |     "import json"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "code",
 17 |    "execution_count": 9,
 18 |    "id": "a1386b5d",
 19 |    "metadata": {},
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>Year of Birth</th>\n",
 43 |        "      <th>Gender</th>\n",
 44 |        "      <th>Ethnicity</th>\n",
 45 |        "      <th>Child's First Name</th>\n",
 46 |        "      <th>Count</th>\n",
 47 |        "      <th>Rank</th>\n",
 48 |        "    </tr>\n",
 49 |        "  </thead>\n",
 50 |        "  <tbody>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>0</th>\n",
 53 |        "      <td>2011</td>\n",
 54 |        "      <td>FEMALE</td>\n",
 55 |        "      <td>HISPANIC</td>\n",
 56 |        "      <td>GERALDINE</td>\n",
 57 |        "      <td>13</td>\n",
 58 |        "      <td>75</td>\n",
 59 |        "    </tr>\n",
 60 |        "    <tr>\n",
 61 |        "      <th>1</th>\n",
 62 |        "      <td>2011</td>\n",
 63 |        "      <td>FEMALE</td>\n",
 64 |        "      <td>HISPANIC</td>\n",
 65 |        "      <td>GIA</td>\n",
 66 |        "      <td>21</td>\n",
 67 |        "      <td>67</td>\n",
 68 |        "    </tr>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>2</th>\n",
 71 |        "      <td>2011</td>\n",
 72 |        "      <td>FEMALE</td>\n",
 73 |        "      <td>HISPANIC</td>\n",
 74 |        "      <td>GIANNA</td>\n",
 75 |        "      <td>49</td>\n",
 76 |        "      <td>42</td>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>3</th>\n",
 80 |        "      <td>2011</td>\n",
 81 |        "      <td>FEMALE</td>\n",
 82 |        "      <td>HISPANIC</td>\n",
 83 |        "      <td>GISELLE</td>\n",
 84 |        "      <td>38</td>\n",
 85 |        "      <td>51</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>4</th>\n",
 89 |        "      <td>2011</td>\n",
 90 |        "      <td>FEMALE</td>\n",
 91 |        "      <td>HISPANIC</td>\n",
 92 |        "      <td>GRACE</td>\n",
 93 |        "      <td>36</td>\n",
 94 |        "      <td>53</td>\n",
 95 |        "    </tr>\n",
 96 |        "    <tr>\n",
 97 |        "      <th>...</th>\n",
 98 |        "      <td>...</td>\n",
 99 |        "      <td>...</td>\n",
100 |        "      <td>...</td>\n",
101 |        "      <td>...</td>\n",
102 |        "      <td>...</td>\n",
103 |        "      <td>...</td>\n",
104 |        "    </tr>\n",
105 |        "    <tr>\n",
106 |        "      <th>57577</th>\n",
107 |        "      <td>2014</td>\n",
108 |        "      <td>MALE</td>\n",
109 |        "      <td>WHITE NON HISPANIC</td>\n",
110 |        "      <td>Yousef</td>\n",
111 |        "      <td>18</td>\n",
112 |        "      <td>94</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>57578</th>\n",
116 |        "      <td>2014</td>\n",
117 |        "      <td>MALE</td>\n",
118 |        "      <td>WHITE NON HISPANIC</td>\n",
119 |        "      <td>Youssef</td>\n",
120 |        "      <td>24</td>\n",
121 |        "      <td>88</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>57579</th>\n",
125 |        "      <td>2014</td>\n",
126 |        "      <td>MALE</td>\n",
127 |        "      <td>WHITE NON HISPANIC</td>\n",
128 |        "      <td>Yusuf</td>\n",
129 |        "      <td>16</td>\n",
130 |        "      <td>96</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>57580</th>\n",
134 |        "      <td>2014</td>\n",
135 |        "      <td>MALE</td>\n",
136 |        "      <td>WHITE NON HISPANIC</td>\n",
137 |        "      <td>Zachary</td>\n",
138 |        "      <td>90</td>\n",
139 |        "      <td>39</td>\n",
140 |        "    </tr>\n",
141 |        "    <tr>\n",
142 |        "      <th>57581</th>\n",
143 |        "      <td>2014</td>\n",
144 |        "      <td>MALE</td>\n",
145 |        "      <td>WHITE NON HISPANIC</td>\n",
146 |        "      <td>Zev</td>\n",
147 |        "      <td>49</td>\n",
148 |        "      <td>65</td>\n",
149 |        "    </tr>\n",
150 |        "  </tbody>\n",
151 |        "</table>\n",
152 |        "<p>57582 rows × 6 columns</p>\n",
153 |        "</div>"
154 |       ],
155 |       "text/plain": [
156 |        "       Year of Birth  Gender           Ethnicity Child's First Name  Count  \\\n",
157 |        "0               2011  FEMALE            HISPANIC          GERALDINE     13   \n",
158 |        "1               2011  FEMALE            HISPANIC                GIA     21   \n",
159 |        "2               2011  FEMALE            HISPANIC             GIANNA     49   \n",
160 |        "3               2011  FEMALE            HISPANIC            GISELLE     38   \n",
161 |        "4               2011  FEMALE            HISPANIC              GRACE     36   \n",
162 |        "...              ...     ...                 ...                ...    ...   \n",
163 |        "57577           2014    MALE  WHITE NON HISPANIC             Yousef     18   \n",
164 |        "57578           2014    MALE  WHITE NON HISPANIC            Youssef     24   \n",
165 |        "57579           2014    MALE  WHITE NON HISPANIC              Yusuf     16   \n",
166 |        "57580           2014    MALE  WHITE NON HISPANIC            Zachary     90   \n",
167 |        "57581           2014    MALE  WHITE NON HISPANIC                Zev     49   \n",
168 |        "\n",
169 |        "       Rank  \n",
170 |        "0        75  \n",
171 |        "1        67  \n",
172 |        "2        42  \n",
173 |        "3        51  \n",
174 |        "4        53  \n",
175 |        "...     ...  \n",
176 |        "57577    94  \n",
177 |        "57578    88  \n",
178 |        "57579    96  \n",
179 |        "57580    39  \n",
180 |        "57581    65  \n",
181 |        "\n",
182 |        "[57582 rows x 6 columns]"
183 |       ]
184 |      },
185 |      "execution_count": 9,
186 |      "metadata": {},
187 |      "output_type": "execute_result"
188 |     }
189 |    ],
190 |    "source": [
191 |     "df = pd.read_csv('Popular_Baby_Names.csv')\n",
192 |     "df"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "code",
197 |    "execution_count": 10,
198 |    "id": "8d4f6743",
199 |    "metadata": {},
200 |    "outputs": [
201 |     {
202 |      "name": "stdout",
203 |      "output_type": "stream",
204 |      "text": [
205 |       "<class 'pandas.core.frame.DataFrame'>\n",
206 |       "RangeIndex: 57582 entries, 0 to 57581\n",
207 |       "Data columns (total 6 columns):\n",
208 |       " #   Column              Non-Null Count  Dtype \n",
209 |       "---  ------              --------------  ----- \n",
210 |       " 0   Year of Birth       57582 non-null  int64 \n",
211 |       " 1   Gender              57582 non-null  object\n",
212 |       " 2   Ethnicity           57582 non-null  object\n",
213 |       " 3   Child's First Name  57582 non-null  object\n",
214 |       " 4   Count               57582 non-null  int64 \n",
215 |       " 5   Rank                57582 non-null  int64 \n",
216 |       "dtypes: int64(3), object(3)\n",
217 |       "memory usage: 2.6+ MB\n"
218 |      ]
219 |     }
220 |    ],
221 |    "source": [
222 |     "df.info()"
223 |    ]
224 |   },
225 |   {
226 |    "cell_type": "code",
227 |    "execution_count": null,
228 |    "id": "cd438718",
229 |    "metadata": {},
230 |    "outputs": [],
231 |    "source": [
232 |     "data = data.sample(frac=1).reset_index(drop=True)\n"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": null,
238 |    "id": "c64d9a65",
239 |    "metadata": {},
240 |    "outputs": [],
241 |    "source": []
242 |   }
243 |  ],
244 |  "metadata": {
245 |   "kernelspec": {
246 |    "display_name": "Python 3 (ipykernel)",
247 |    "language": "python",
248 |    "name": "python3"
249 |   },
250 |   "language_info": {
251 |    "codemirror_mode": {
252 |     "name": "ipython",
253 |     "version": 3
254 |    },
255 |    "file_extension": ".py",
256 |    "mimetype": "text/x-python",
257 |    "name": "python",
258 |    "nbconvert_exporter": "python",
259 |    "pygments_lexer": "ipython3",
260 |    "version": "3.11.3"
261 |   }
262 |  },
263 |  "nbformat": 4,
264 |  "nbformat_minor": 5
265 | }
266 | 


--------------------------------------------------------------------------------
/Data-Splitter.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "38f5b7b3",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd \n",
 11 |     "import pyodbc\n",
 12 |     "import json"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "code",
 17 |    "execution_count": 2,
 18 |    "id": "01221e86",
 19 |    "metadata": {},
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>Year of Birth</th>\n",
 43 |        "      <th>Gender</th>\n",
 44 |        "      <th>Ethnicity</th>\n",
 45 |        "      <th>Child's First Name</th>\n",
 46 |        "      <th>Count</th>\n",
 47 |        "      <th>Rank</th>\n",
 48 |        "    </tr>\n",
 49 |        "  </thead>\n",
 50 |        "  <tbody>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>0</th>\n",
 53 |        "      <td>2011</td>\n",
 54 |        "      <td>FEMALE</td>\n",
 55 |        "      <td>HISPANIC</td>\n",
 56 |        "      <td>GERALDINE</td>\n",
 57 |        "      <td>13</td>\n",
 58 |        "      <td>75</td>\n",
 59 |        "    </tr>\n",
 60 |        "    <tr>\n",
 61 |        "      <th>1</th>\n",
 62 |        "      <td>2011</td>\n",
 63 |        "      <td>FEMALE</td>\n",
 64 |        "      <td>HISPANIC</td>\n",
 65 |        "      <td>GIA</td>\n",
 66 |        "      <td>21</td>\n",
 67 |        "      <td>67</td>\n",
 68 |        "    </tr>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>2</th>\n",
 71 |        "      <td>2011</td>\n",
 72 |        "      <td>FEMALE</td>\n",
 73 |        "      <td>HISPANIC</td>\n",
 74 |        "      <td>GIANNA</td>\n",
 75 |        "      <td>49</td>\n",
 76 |        "      <td>42</td>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>3</th>\n",
 80 |        "      <td>2011</td>\n",
 81 |        "      <td>FEMALE</td>\n",
 82 |        "      <td>HISPANIC</td>\n",
 83 |        "      <td>GISELLE</td>\n",
 84 |        "      <td>38</td>\n",
 85 |        "      <td>51</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>4</th>\n",
 89 |        "      <td>2011</td>\n",
 90 |        "      <td>FEMALE</td>\n",
 91 |        "      <td>HISPANIC</td>\n",
 92 |        "      <td>GRACE</td>\n",
 93 |        "      <td>36</td>\n",
 94 |        "      <td>53</td>\n",
 95 |        "    </tr>\n",
 96 |        "    <tr>\n",
 97 |        "      <th>...</th>\n",
 98 |        "      <td>...</td>\n",
 99 |        "      <td>...</td>\n",
100 |        "      <td>...</td>\n",
101 |        "      <td>...</td>\n",
102 |        "      <td>...</td>\n",
103 |        "      <td>...</td>\n",
104 |        "    </tr>\n",
105 |        "    <tr>\n",
106 |        "      <th>57577</th>\n",
107 |        "      <td>2014</td>\n",
108 |        "      <td>MALE</td>\n",
109 |        "      <td>WHITE NON HISPANIC</td>\n",
110 |        "      <td>Yousef</td>\n",
111 |        "      <td>18</td>\n",
112 |        "      <td>94</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>57578</th>\n",
116 |        "      <td>2014</td>\n",
117 |        "      <td>MALE</td>\n",
118 |        "      <td>WHITE NON HISPANIC</td>\n",
119 |        "      <td>Youssef</td>\n",
120 |        "      <td>24</td>\n",
121 |        "      <td>88</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>57579</th>\n",
125 |        "      <td>2014</td>\n",
126 |        "      <td>MALE</td>\n",
127 |        "      <td>WHITE NON HISPANIC</td>\n",
128 |        "      <td>Yusuf</td>\n",
129 |        "      <td>16</td>\n",
130 |        "      <td>96</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>57580</th>\n",
134 |        "      <td>2014</td>\n",
135 |        "      <td>MALE</td>\n",
136 |        "      <td>WHITE NON HISPANIC</td>\n",
137 |        "      <td>Zachary</td>\n",
138 |        "      <td>90</td>\n",
139 |        "      <td>39</td>\n",
140 |        "    </tr>\n",
141 |        "    <tr>\n",
142 |        "      <th>57581</th>\n",
143 |        "      <td>2014</td>\n",
144 |        "      <td>MALE</td>\n",
145 |        "      <td>WHITE NON HISPANIC</td>\n",
146 |        "      <td>Zev</td>\n",
147 |        "      <td>49</td>\n",
148 |        "      <td>65</td>\n",
149 |        "    </tr>\n",
150 |        "  </tbody>\n",
151 |        "</table>\n",
152 |        "<p>57582 rows × 6 columns</p>\n",
153 |        "</div>"
154 |       ],
155 |       "text/plain": [
156 |        "       Year of Birth  Gender           Ethnicity Child's First Name  Count  \\\n",
157 |        "0               2011  FEMALE            HISPANIC          GERALDINE     13   \n",
158 |        "1               2011  FEMALE            HISPANIC                GIA     21   \n",
159 |        "2               2011  FEMALE            HISPANIC             GIANNA     49   \n",
160 |        "3               2011  FEMALE            HISPANIC            GISELLE     38   \n",
161 |        "4               2011  FEMALE            HISPANIC              GRACE     36   \n",
162 |        "...              ...     ...                 ...                ...    ...   \n",
163 |        "57577           2014    MALE  WHITE NON HISPANIC             Yousef     18   \n",
164 |        "57578           2014    MALE  WHITE NON HISPANIC            Youssef     24   \n",
165 |        "57579           2014    MALE  WHITE NON HISPANIC              Yusuf     16   \n",
166 |        "57580           2014    MALE  WHITE NON HISPANIC            Zachary     90   \n",
167 |        "57581           2014    MALE  WHITE NON HISPANIC                Zev     49   \n",
168 |        "\n",
169 |        "       Rank  \n",
170 |        "0        75  \n",
171 |        "1        67  \n",
172 |        "2        42  \n",
173 |        "3        51  \n",
174 |        "4        53  \n",
175 |        "...     ...  \n",
176 |        "57577    94  \n",
177 |        "57578    88  \n",
178 |        "57579    96  \n",
179 |        "57580    39  \n",
180 |        "57581    65  \n",
181 |        "\n",
182 |        "[57582 rows x 6 columns]"
183 |       ]
184 |      },
185 |      "execution_count": 2,
186 |      "metadata": {},
187 |      "output_type": "execute_result"
188 |     }
189 |    ],
190 |    "source": [
191 |     "df = pd.read_csv('Popular_Baby_Names.csv')\n",
192 |     "df"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "code",
197 |    "execution_count": 3,
198 |    "id": "cc99b3f2",
199 |    "metadata": {},
200 |    "outputs": [
201 |     {
202 |      "name": "stdout",
203 |      "output_type": "stream",
204 |      "text": [
205 |       "<class 'pandas.core.frame.DataFrame'>\n",
206 |       "RangeIndex: 57582 entries, 0 to 57581\n",
207 |       "Data columns (total 6 columns):\n",
208 |       " #   Column              Non-Null Count  Dtype \n",
209 |       "---  ------              --------------  ----- \n",
210 |       " 0   Year of Birth       57582 non-null  int64 \n",
211 |       " 1   Gender              57582 non-null  object\n",
212 |       " 2   Ethnicity           57582 non-null  object\n",
213 |       " 3   Child's First Name  57582 non-null  object\n",
214 |       " 4   Count               57582 non-null  int64 \n",
215 |       " 5   Rank                57582 non-null  int64 \n",
216 |       "dtypes: int64(3), object(3)\n",
217 |       "memory usage: 2.6+ MB\n"
218 |      ]
219 |     }
220 |    ],
221 |    "source": [
222 |     "df.info()"
223 |    ]
224 |   },
225 |   {
226 |    "cell_type": "code",
227 |    "execution_count": 4,
228 |    "id": "67bd91e5",
229 |    "metadata": {},
230 |    "outputs": [],
231 |    "source": [
232 |     "# Mélanger les lignes pour une répartition aléatoire des données\n",
233 |     "df = df.sample(frac=1).reset_index(drop=True)"
234 |    ]
235 |   },
236 |   {
237 |    "cell_type": "code",
238 |    "execution_count": 5,
239 |    "id": "861978ed",
240 |    "metadata": {},
241 |    "outputs": [
242 |     {
243 |      "data": {
244 |       "text/html": [
245 |        "<div>\n",
246 |        "<style scoped>\n",
247 |        "    .dataframe tbody tr th:only-of-type {\n",
248 |        "        vertical-align: middle;\n",
249 |        "    }\n",
250 |        "\n",
251 |        "    .dataframe tbody tr th {\n",
252 |        "        vertical-align: top;\n",
253 |        "    }\n",
254 |        "\n",
255 |        "    .dataframe thead th {\n",
256 |        "        text-align: right;\n",
257 |        "    }\n",
258 |        "</style>\n",
259 |        "<table border=\"1\" class=\"dataframe\">\n",
260 |        "  <thead>\n",
261 |        "    <tr style=\"text-align: right;\">\n",
262 |        "      <th></th>\n",
263 |        "      <th>Year of Birth</th>\n",
264 |        "      <th>Gender</th>\n",
265 |        "      <th>Ethnicity</th>\n",
266 |        "      <th>Child's First Name</th>\n",
267 |        "      <th>Count</th>\n",
268 |        "      <th>Rank</th>\n",
269 |        "    </tr>\n",
270 |        "  </thead>\n",
271 |        "  <tbody>\n",
272 |        "    <tr>\n",
273 |        "      <th>0</th>\n",
274 |        "      <td>2014</td>\n",
275 |        "      <td>MALE</td>\n",
276 |        "      <td>ASIAN AND PACIFIC ISLANDER</td>\n",
277 |        "      <td>Jeffrey</td>\n",
278 |        "      <td>17</td>\n",
279 |        "      <td>51</td>\n",
280 |        "    </tr>\n",
281 |        "    <tr>\n",
282 |        "      <th>1</th>\n",
283 |        "      <td>2013</td>\n",
284 |        "      <td>MALE</td>\n",
285 |        "      <td>ASIAN AND PACIFIC ISLANDER</td>\n",
286 |        "      <td>Jordan</td>\n",
287 |        "      <td>19</td>\n",
288 |        "      <td>48</td>\n",
289 |        "    </tr>\n",
290 |        "    <tr>\n",
291 |        "      <th>2</th>\n",
292 |        "      <td>2014</td>\n",
293 |        "      <td>MALE</td>\n",
294 |        "      <td>HISPANIC</td>\n",
295 |        "      <td>Kai</td>\n",
296 |        "      <td>13</td>\n",
297 |        "      <td>95</td>\n",
298 |        "    </tr>\n",
299 |        "    <tr>\n",
300 |        "      <th>3</th>\n",
301 |        "      <td>2012</td>\n",
302 |        "      <td>MALE</td>\n",
303 |        "      <td>HISPANIC</td>\n",
304 |        "      <td>ISAIAH</td>\n",
305 |        "      <td>79</td>\n",
306 |        "      <td>43</td>\n",
307 |        "    </tr>\n",
308 |        "    <tr>\n",
309 |        "      <th>4</th>\n",
310 |        "      <td>2013</td>\n",
311 |        "      <td>FEMALE</td>\n",
312 |        "      <td>WHITE NON HISPANIC</td>\n",
313 |        "      <td>Ester</td>\n",
314 |        "      <td>10</td>\n",
315 |        "      <td>82</td>\n",
316 |        "    </tr>\n",
317 |        "    <tr>\n",
318 |        "      <th>...</th>\n",
319 |        "      <td>...</td>\n",
320 |        "      <td>...</td>\n",
321 |        "      <td>...</td>\n",
322 |        "      <td>...</td>\n",
323 |        "      <td>...</td>\n",
324 |        "      <td>...</td>\n",
325 |        "    </tr>\n",
326 |        "    <tr>\n",
327 |        "      <th>57577</th>\n",
328 |        "      <td>2011</td>\n",
329 |        "      <td>FEMALE</td>\n",
330 |        "      <td>HISPANIC</td>\n",
331 |        "      <td>AMY</td>\n",
332 |        "      <td>87</td>\n",
333 |        "      <td>17</td>\n",
334 |        "    </tr>\n",
335 |        "    <tr>\n",
336 |        "      <th>57578</th>\n",
337 |        "      <td>2012</td>\n",
338 |        "      <td>MALE</td>\n",
339 |        "      <td>HISPANIC</td>\n",
340 |        "      <td>JORDAN</td>\n",
341 |        "      <td>57</td>\n",
342 |        "      <td>58</td>\n",
343 |        "    </tr>\n",
344 |        "    <tr>\n",
345 |        "      <th>57579</th>\n",
346 |        "      <td>2013</td>\n",
347 |        "      <td>MALE</td>\n",
348 |        "      <td>WHITE NON HISPANIC</td>\n",
349 |        "      <td>Meir</td>\n",
350 |        "      <td>40</td>\n",
351 |        "      <td>70</td>\n",
352 |        "    </tr>\n",
353 |        "    <tr>\n",
354 |        "      <th>57580</th>\n",
355 |        "      <td>2013</td>\n",
356 |        "      <td>FEMALE</td>\n",
357 |        "      <td>HISPANIC</td>\n",
358 |        "      <td>Kendra</td>\n",
359 |        "      <td>17</td>\n",
360 |        "      <td>71</td>\n",
361 |        "    </tr>\n",
362 |        "    <tr>\n",
363 |        "      <th>57581</th>\n",
364 |        "      <td>2014</td>\n",
365 |        "      <td>FEMALE</td>\n",
366 |        "      <td>BLACK NON HISPANIC</td>\n",
367 |        "      <td>Alexandria</td>\n",
368 |        "      <td>10</td>\n",
369 |        "      <td>41</td>\n",
370 |        "    </tr>\n",
371 |        "  </tbody>\n",
372 |        "</table>\n",
373 |        "<p>57582 rows × 6 columns</p>\n",
374 |        "</div>"
375 |       ],
376 |       "text/plain": [
377 |        "       Year of Birth  Gender                   Ethnicity Child's First Name  \\\n",
378 |        "0               2014    MALE  ASIAN AND PACIFIC ISLANDER            Jeffrey   \n",
379 |        "1               2013    MALE  ASIAN AND PACIFIC ISLANDER             Jordan   \n",
380 |        "2               2014    MALE                    HISPANIC                Kai   \n",
381 |        "3               2012    MALE                    HISPANIC             ISAIAH   \n",
382 |        "4               2013  FEMALE          WHITE NON HISPANIC              Ester   \n",
383 |        "...              ...     ...                         ...                ...   \n",
384 |        "57577           2011  FEMALE                    HISPANIC                AMY   \n",
385 |        "57578           2012    MALE                    HISPANIC             JORDAN   \n",
386 |        "57579           2013    MALE          WHITE NON HISPANIC               Meir   \n",
387 |        "57580           2013  FEMALE                    HISPANIC             Kendra   \n",
388 |        "57581           2014  FEMALE          BLACK NON HISPANIC         Alexandria   \n",
389 |        "\n",
390 |        "       Count  Rank  \n",
391 |        "0         17    51  \n",
392 |        "1         19    48  \n",
393 |        "2         13    95  \n",
394 |        "3         79    43  \n",
395 |        "4         10    82  \n",
396 |        "...      ...   ...  \n",
397 |        "57577     87    17  \n",
398 |        "57578     57    58  \n",
399 |        "57579     40    70  \n",
400 |        "57580     17    71  \n",
401 |        "57581     10    41  \n",
402 |        "\n",
403 |        "[57582 rows x 6 columns]"
404 |       ]
405 |      },
406 |      "execution_count": 5,
407 |      "metadata": {},
408 |      "output_type": "execute_result"
409 |     }
410 |    ],
411 |    "source": [
412 |     "df"
413 |    ]
414 |   },
415 |   {
416 |    "cell_type": "code",
417 |    "execution_count": 6,
418 |    "id": "e73b61b4",
419 |    "metadata": {},
420 |    "outputs": [],
421 |    "source": [
422 |     "# Calculer le nombre de lignes pour chaque partie\n",
423 |     "total_rows = len(df)\n",
424 |     "json_rows = int(0.3 * total_rows)\n",
425 |     "db_rows = int(0.3 * total_rows)\n",
426 |     "csv_rows = total_rows - json_rows - db_rows"
427 |    ]
428 |   },
429 |   {
430 |    "cell_type": "code",
431 |    "execution_count": 7,
432 |    "id": "c6fa9de0",
433 |    "metadata": {},
434 |    "outputs": [],
435 |    "source": [
436 |     "# Diviser les données en trois parties\n",
437 |     "json_data = df[:json_rows]\n",
438 |     "db_data = df[json_rows:json_rows + db_rows]\n",
439 |     "csv_data = df[json_rows + db_rows:]"
440 |    ]
441 |   },
442 |   {
443 |    "cell_type": "code",
444 |    "execution_count": 8,
445 |    "id": "e7113975",
446 |    "metadata": {},
447 |    "outputs": [],
448 |    "source": [
449 |     "# Sauvegarder les données au format JSON\n",
450 |     "json_data.to_json(\"donnees.json\", orient=\"records\", lines=True)\n"
451 |    ]
452 |   },
453 |   {
454 |    "cell_type": "code",
455 |    "execution_count": 9,
456 |    "id": "db05b81b",
457 |    "metadata": {},
458 |    "outputs": [
459 |     {
460 |      "name": "stdout",
461 |      "output_type": "stream",
462 |      "text": [
463 |       "Microsoft SQL Server 2022 (RTM) - 16.0.1000.6 (X64) \n",
464 |       "\tOct  8 2022 05:58:25 \n",
465 |       "\tCopyright (C) 2022 Microsoft Corporation\n",
466 |       "\tExpress Edition (64-bit) on Windows 10 Pro 10.0 <X64> (Build 19045: )\n",
467 |       "\n"
468 |      ]
469 |     }
470 |    ],
471 |    "source": [
472 |     "# Se connecter à la base de données SQL Server\n",
473 |     "conn = pyodbc.connect(\"Driver={SQL Server};Server=LAPTOP-IGO4LBSV\\SQLEXPRESS;Database=Popular_Baby_Names;Trusted_Connection=yes;\")\n",
474 |     "cursor = conn.cursor()\n",
475 |     "\n",
476 |     "cursor.execute(\"SELECT @@version;\")\n",
477 |     "row = cursor.fetchone()\n",
478 |     "while row: \n",
479 |     "    print(row[0])\n",
480 |     "    row = cursor.fetchone()\n"
481 |    ]
482 |   },
483 |   {
484 |    "cell_type": "code",
485 |    "execution_count": 29,
486 |    "id": "b98aa821",
487 |    "metadata": {
488 |     "scrolled": true
489 |    },
490 |    "outputs": [
491 |     {
492 |      "name": "stdout",
493 |      "output_type": "stream",
494 |      "text": [
495 |       "<class 'pandas.core.frame.DataFrame'>\n",
496 |       "RangeIndex: 57582 entries, 0 to 57581\n",
497 |       "Data columns (total 6 columns):\n",
498 |       " #   Column              Non-Null Count  Dtype \n",
499 |       "---  ------              --------------  ----- \n",
500 |       " 0   Year of Birth       57582 non-null  int64 \n",
501 |       " 1   Gender              57582 non-null  object\n",
502 |       " 2   Ethnicity           57582 non-null  object\n",
503 |       " 3   Child's First Name  57582 non-null  object\n",
504 |       " 4   Count               57582 non-null  int64 \n",
505 |       " 5   Rank                57582 non-null  int64 \n",
506 |       "dtypes: int64(3), object(3)\n",
507 |       "memory usage: 2.6+ MB\n"
508 |      ]
509 |     }
510 |    ],
511 |    "source": [
512 |     "df.info()"
513 |    ]
514 |   },
515 |   {
516 |    "cell_type": "code",
517 |    "execution_count": null,
518 |    "id": "e99b1194",
519 |    "metadata": {},
520 |    "outputs": [],
521 |    "source": [
522 |     "# Créer une table dans la base de données\n",
523 |     "cursor = conn.cursor()\n",
524 |     "cursor.execute('''create table Popular_Baby_Names (\n",
525 |     "               id INT PRIMARY KEY NOT NULL IDENTITY ,\n",
526 |     "               year int,\n",
527 |     "               Gender varchar(55),         \n",
528 |     "               Ethnicity varchar(100),\n",
529 |     "               FirstName varchar(100),\n",
530 |     "               Count int,\n",
531 |     "               Rank int          \n",
532 |     "              )\n",
533 |     "               ''')\n",
534 |     "cursor.commit()\n"
535 |    ]
536 |   },
537 |   {
538 |    "cell_type": "code",
539 |    "execution_count": 12,
540 |    "id": "6d8974c7",
541 |    "metadata": {},
542 |    "outputs": [
543 |     {
544 |      "name": "stdout",
545 |      "output_type": "stream",
546 |      "text": [
547 |       "<class 'pandas.core.frame.DataFrame'>\n",
548 |       "RangeIndex: 57582 entries, 0 to 57581\n",
549 |       "Data columns (total 6 columns):\n",
550 |       " #   Column              Non-Null Count  Dtype \n",
551 |       "---  ------              --------------  ----- \n",
552 |       " 0   Year of Birth       57582 non-null  int64 \n",
553 |       " 1   Gender              57582 non-null  object\n",
554 |       " 2   Ethnicity           57582 non-null  object\n",
555 |       " 3   Child's First Name  57582 non-null  object\n",
556 |       " 4   Count               57582 non-null  int64 \n",
557 |       " 5   Rank                57582 non-null  int64 \n",
558 |       "dtypes: int64(3), object(3)\n",
559 |       "memory usage: 2.6+ MB\n"
560 |      ]
561 |     }
562 |    ],
563 |    "source": [
564 |     "df.info()"
565 |    ]
566 |   },
567 |   {
568 |    "cell_type": "code",
569 |    "execution_count": 13,
570 |    "id": "3684104c",
571 |    "metadata": {},
572 |    "outputs": [],
573 |    "source": [
574 |     "cursor = conn.cursor()\n",
575 |     "\n",
576 |     "for index, row in db_data.iterrows():\n",
577 |     "        cursor.execute(\"INSERT INTO Popular_Baby_Names (year, Gender,Ethnicity,FirstName,Count,Rank) VALUES (?, ?, ?, ?, ?, ?)\", row[\"Year of Birth\"], row[\"Gender\"], row[\"Ethnicity\"], row[\"Child's First Name\"], row[\"Count\"], row[\"Rank\"])\n",
578 |     "\n",
579 |     "cursor.commit()\n",
580 |     "cursor.close()"
581 |    ]
582 |   },
583 |   {
584 |    "cell_type": "code",
585 |    "execution_count": 15,
586 |    "id": "c6bcde28",
587 |    "metadata": {},
588 |    "outputs": [],
589 |    "source": [
590 |     "# Sauvegarder les données au format CSV\n",
591 |     "csv_data.to_csv(\"donnees.csv\", index=False, header=False)"
592 |    ]
593 |   }
594 |  ],
595 |  "metadata": {
596 |   "kernelspec": {
597 |    "display_name": "Python 3 (ipykernel)",
598 |    "language": "python",
599 |    "name": "python3"
600 |   },
601 |   "language_info": {
602 |    "codemirror_mode": {
603 |     "name": "ipython",
604 |     "version": 3
605 |    },
606 |    "file_extension": ".py",
607 |    "mimetype": "text/x-python",
608 |    "name": "python",
609 |    "nbconvert_exporter": "python",
610 |    "pygments_lexer": "ipython3",
611 |    "version": "3.11.3"
612 |   }
613 |  },
614 |  "nbformat": 4,
615 |  "nbformat_minor": 5
616 | }
617 | 


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