{
"cells": [
{
"cell_type": "markdown",
"id": "91de22bd",
"metadata": {},
"source": [
"# Матрица выводов по сегментам\n",
"\n",
"Ответ на фидбек организаторов: делаем матрицу по возрастным сегментам и типам каналов, фиксируем закономерности и идеи изменений."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "16660d45",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-12T18:42:58.838813Z",
"iopub.status.busy": "2025-12-12T18:42:58.838553Z",
"iopub.status.idle": "2025-12-12T18:43:05.571711Z",
"shell.execute_reply": "2025-12-12T18:43:05.569612Z"
}
},
"outputs": [],
"source": [
"import sqlite3\n",
"from pathlib import Path\n",
"import sys\n",
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"sns.set_theme(style=\"whitegrid\")\n",
"plt.rcParams[\"figure.figsize\"] = (10, 5)\n",
"\n",
"project_root = Path.cwd().resolve()\n",
"if not (project_root / \"preanalysis\").exists():\n",
" project_root = project_root.parent\n",
"sys.path.append(str(project_root / \"preanalysis\"))\n",
"import eda_utils as eda\n",
"\n",
"db_path = project_root / \"dataset\" / \"ds.sqlite\"\n",
"conn = sqlite3.connect(db_path)\n",
"df = pd.read_sql_query(\"select * from communications\", conn, parse_dates=[\"business_dt\"])\n",
"conn.close()\n",
"\n",
"age_bins = [15, 25, 35, 45, 55, 120]\n",
"age_labels = [\"15-24\", \"25-34\", \"35-44\", \"45-54\", \"55+\"]\n",
"df[\"age_segment\"] = pd.cut(df[\"age\"], bins=age_bins, labels=age_labels, right=False, include_lowest=True)\n",
"\n",
"for cols, name in [\n",
" (eda.ACTIVE_IMP_COLS, \"active_imp_total\"),\n",
" (eda.PASSIVE_IMP_COLS, \"passive_imp_total\"),\n",
" (eda.ACTIVE_CLICK_COLS, \"active_click_total\"),\n",
" (eda.PASSIVE_CLICK_COLS, \"passive_click_total\"),\n",
" (eda.ORDER_COLS, \"orders_amt_total\"),\n",
"]:\n",
" df[name] = df[cols].sum(axis=1)\n",
"\n",
"df[\"imp_total\"] = df[\"active_imp_total\"] + df[\"passive_imp_total\"]\n",
"df[\"click_total\"] = df[\"active_click_total\"] + df[\"passive_click_total\"]\n",
"\n",
"df[\"ctr_active\"] = eda.safe_divide(df[\"active_click_total\"], df[\"active_imp_total\"])\n",
"df[\"ctr_passive\"] = eda.safe_divide(df[\"passive_click_total\"], df[\"passive_imp_total\"])\n",
"df[\"ctr_all\"] = eda.safe_divide(df[\"click_total\"], df[\"imp_total\"])\n",
"df[\"cr_click2order\"] = eda.safe_divide(df[\"orders_amt_total\"], df[\"click_total\"])\n"
]
},
{
"cell_type": "markdown",
"id": "317a8a38",
"metadata": {},
"source": [
"## Матрица CTR/CR по 5 возрастным сегментам и каналам"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "6743acba",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-12T18:43:05.578992Z",
"iopub.status.busy": "2025-12-12T18:43:05.578499Z",
"iopub.status.idle": "2025-12-12T18:43:05.614188Z",
"shell.execute_reply": "2025-12-12T18:43:05.612157Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1031533/2377539060.py:1: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
" segment_perf = df.groupby(\"age_segment\").agg(\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" ctr_active | \n",
" ctr_passive | \n",
" cr_active | \n",
" cr_passive | \n",
"
\n",
" \n",
" | age_segment | \n",
" | \n",
" | \n",
" | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | 15-24 | \n",
" 0.669682 | \n",
" 0.026672 | \n",
" 0.057846 | \n",
" 0.627820 | \n",
"
\n",
" \n",
" | 25-34 | \n",
" 0.675315 | \n",
" 0.035316 | \n",
" 0.087974 | \n",
" 0.707119 | \n",
"
\n",
" \n",
" | 35-44 | \n",
" 0.672207 | \n",
" 0.037188 | \n",
" 0.090557 | \n",
" 0.741876 | \n",
"
\n",
" \n",
" | 45-54 | \n",
" 0.668323 | \n",
" 0.040513 | \n",
" 0.077198 | \n",
" 0.631981 | \n",
"
\n",
" \n",
" | 55+ | \n",
" 0.668371 | \n",
" 0.045245 | \n",
" 0.077028 | \n",
" 0.594488 | \n",
"
\n",
" \n",
"
\n",
"