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

Modification de la base df1_product_purchased

Browse Source
This commit is contained in:
Antoine JOUBREL 2024-02-06 21:09:08 +00:00
parent b2a6ae0929
commit 5d4dde93f3
1 changed files with 28 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
0_Cleaning_and_merge.ipynb
View File

@ -79,7 +79,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"/tmp/ipykernel_3658/4081512283.py:10: DtypeWarning: Columns (1) have mixed types. Specify dtype option on import or set low_memory=False.\n", "/tmp/ipykernel_492/4081512283.py:10: DtypeWarning: Columns (1) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df = pd.read_csv(file_in)\n" " df = pd.read_csv(file_in)\n"
] ]
} }
@ -242,17 +242,17 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"/tmp/ipykernel_3658/1591303091.py:5: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/1591303091.py:5: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n", "A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" tickets.rename(columns = {'id' : 'ticket_id'}, inplace = True)\n", " tickets.rename(columns = {'id' : 'ticket_id'}, inplace = True)\n",
"/tmp/ipykernel_3658/1591303091.py:9: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/1591303091.py:9: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n", "A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" suppliers.rename(columns = {'name' : 'supplier_name'}, inplace = True)\n", " suppliers.rename(columns = {'name' : 'supplier_name'}, inplace = True)\n",
"/tmp/ipykernel_3658/1591303091.py:13: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/1591303091.py:13: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n", "A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
@ -596,7 +596,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"/tmp/ipykernel_3658/3848597476.py:4: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/3848597476.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n", "A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
@ -810,19 +810,19 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"/tmp/ipykernel_3658/1967867975.py:15: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/1967867975.py:15: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n", "A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n", "Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df[column_name] = pd.to_datetime(df[column_name], utc = True, format = 'ISO8601')\n", " df[column_name] = pd.to_datetime(df[column_name], utc = True, format = 'ISO8601')\n",
"/tmp/ipykernel_3658/1967867975.py:15: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/1967867975.py:15: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n", "A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n", "Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df[column_name] = pd.to_datetime(df[column_name], utc = True, format = 'ISO8601')\n", " df[column_name] = pd.to_datetime(df[column_name], utc = True, format = 'ISO8601')\n",
"/tmp/ipykernel_3658/1967867975.py:15: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/1967867975.py:15: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n", "A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n", "Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n", "\n",
@ -1010,7 +1010,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"/tmp/ipykernel_3658/3700263836.py:11: SettingWithCopyWarning: \n", "/tmp/ipykernel_492/3700263836.py:11: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n", "A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n", "\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
@ -2009,6 +2009,17 @@
"products_global.head()" "products_global.head()"
] ]
}, },
{
"cell_type": "code",
"execution_count": 32,
"id": "98f78cd5-b694-4cc6-b033-20170aa13e8d",
"metadata": {},
"outputs": [],
"source": [
"# Fusion liée au product\n",
"df1_products_purchased = pd.merge(df1_ticket_information, products_global, left_on = 'product_id', right_on = 'id_products', how = 'inner')"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "7c3211a5-a851-43bc-a1f0-b39d51857fb7", "id": "7c3211a5-a851-43bc-a1f0-b39d51857fb7",
@ -2019,28 +2030,25 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 32, "execution_count": 33,
"id": "46de1912-4a66-46e5-8b9e-7768b2d2723b", "id": "46de1912-4a66-46e5-8b9e-7768b2d2723b",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Fusion liée au product\n", "# Fusion avec KPI liés au customer\n",
"df1_products_purchased = pd.merge(df1_tickets_kpi, products_global, left_on = 'product_id', right_on = 'id_products', how = 'inner')\n", "df1_customer = pd.merge(df1_customerplus_clean, df1_campaigns_kpi, on = 'customer_id', how = 'left')"
"\n",
"# Fusion liée au customer\n",
"df1_customer = pd.merge(df1_customerplus_clean, df1_campaigns_kpi, on = 'customer_id', how = 'left')\n",
"\n",
"# Fusion product et customer\n",
"df1_customer_product = pd.merge(df1_customer, df1_products_purchased, on = 'customer_id', how = 'left')"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 34,
"id": "1e42a790-b215-4107-a969-85005da06ebd", "id": "1e42a790-b215-4107-a969-85005da06ebd",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": [
"# Fusion avec KPI liés au comportement d'achat\n",
"# df1_customer_product = pd.merge(df1_customer, df1_products_purchased, on = 'customer_id', how = 'left')"
]
} }
], ],
"metadata": { "metadata": {