ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Complétion brouillon

Browse Source
This commit is contained in:
Antoine JOUBREL 2024-03-27 18:55:11 +00:00
parent 0ffbe06b12
commit be0bcda0ba
1 changed files with 29 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
Exploration_billet_AJ.ipynb
View File

@ -10,7 +10,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 22,
"id": "b1a5b9d3", "id": "b1a5b9d3",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -20,7 +20,9 @@
"import os\n", "import os\n",
"import s3fs\n", "import s3fs\n",
"import re\n", "import re\n",
"import warnings" "import warnings\n",
"import io\n",
"import matplotlib.pyplot as plt\n"
] ]
}, },
{ {
@ -97,6 +99,24 @@
" df.to_csv(file_out, index = False)" " df.to_csv(file_out, index = False)"
] ]
}, },
{
"cell_type": "code",
"execution_count": 15,
"id": "108fc5ef-c56a-4f03-a867-943d9d6492fd",
"metadata": {},
"outputs": [],
"source": [
"def save_file_s3(File_name, type_of_activity):\n",
" image_buffer = io.BytesIO()\n",
" plt.savefig(image_buffer, format='png')\n",
" image_buffer.seek(0)\n",
" FILE_PATH = f\"projet-bdc2324-team1/stat_desc/{type_of_activity}/\"\n",
" FILE_PATH_OUT_S3 = FILE_PATH + File_name + type_of_activity + '.png'\n",
" with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:\n",
" s3_file.write(image_buffer.read())\n",
" plt.close()"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "ccf597b0-b459-4ea5-baf0-5ba8c90915e4", "id": "ccf597b0-b459-4ea5-baf0-5ba8c90915e4",
@ -599,7 +619,7 @@
" 'sport': ['5', '6', '7', '8', '9'],\n", " 'sport': ['5', '6', '7', '8', '9'],\n",
" 'musique' : ['10', '11', '12', '13', '14']}\n", " 'musique' : ['10', '11', '12', '13', '14']}\n",
"\n", "\n",
"nb_compagnie = companies['sport']\n", "nb_compagnie = companies['mu']\n",
"\n", "\n",
"def load_files(nb_compagnie):\n", "def load_files(nb_compagnie):\n",
" targets = pd.DataFrame()\n", " targets = pd.DataFrame()\n",
@ -632,13 +652,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 21, "execution_count": 27,
"id": "3c911274-0ebd-49af-9487-26524ba20e74", "id": "3c911274-0ebd-49af-9487-26524ba20e74",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"\n", "\n",
"def target_description(targets):\n", "def target_description(targets, type_of_activity):\n",
"\n", "\n",
" describe_target = targets.groupby('number_company').agg(\n", " describe_target = targets.groupby('number_company').agg(\n",
" prop_target_jeune=('target_jeune', lambda x: (x.sum() / x.count())*100),\n", " prop_target_jeune=('target_jeune', lambda x: (x.sum() / x.count())*100),\n",
@ -665,12 +685,13 @@
" # Adding a legend\n", " # Adding a legend\n",
" plot.legend([\"Youth\", \"School\", \"Enterprise\", \"Family\", \"Optin\", \"Optout\", \"Newsletter\", \"Subscriber\"], title=\"Target Category\")\n", " plot.legend([\"Youth\", \"School\", \"Enterprise\", \"Family\", \"Optin\", \"Optout\", \"Newsletter\", \"Subscriber\"], title=\"Target Category\")\n",
"\n", "\n",
" # save_file_s3(\"target_category_proportion_\", type_of_activity)\n",
" return plot" " return plot"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 22, "execution_count": 28,
"id": "af62ecef-9120-4107-af3e-512588a96800", "id": "af62ecef-9120-4107-af3e-512588a96800",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -680,7 +701,7 @@
"<Axes: title={'center': 'Distribution of Targets by Category'}, xlabel='Company Number', ylabel='Target Proportion'>" "<Axes: title={'center': 'Distribution of Targets by Category'}, xlabel='Company Number', ylabel='Target Proportion'>"
] ]
}, },
"execution_count": 22, "execution_count": 28,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
}, },
@ -696,7 +717,7 @@
} }
], ],
"source": [ "source": [
"target_description(targets)" "target_description(targets, 'sport')"
] ]
}, },
{ {