{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "import numpy as np\n",
    "\n",
    "# Load CSV file\n",
    "df = pd.read_csv('churn.csv')\n",
    "\n",
    "category_labels = {\n",
    "    'quick-exit': 'Free trial only',\n",
    "    'fair-trial': '74 day churn',\n",
    "    'short-termer': '6 month churn',\n",
    "    'active-user': 'No churn'\n",
    "}\n",
    "timeframe_labels = {\n",
    "    'short term': 'During free trial',\n",
    "    'medium term': 'After trial, before 90 days',\n",
    "    'long term': 'After 90 days, first 6 months'\n",
    "}\n",
    "\n",
    "def fix_dataset_label(k):\n",
    "    parts = k.split('_')\n",
    "    if \"term\" in parts:\n",
    "        timeframe = timeframe_labels[parts[-2:].join(\" \")]\n",
    "        name = parts[0:-2].join(\" \").title()\n",
    "    else:\n",
    "        timeframe = 'Lifetime'\n",
    "        name = parts.join(\" \").title()\n",
    "    return f\"{name}: {timeframe}\"\n",
    "\n",
    "def x_labels(categories):\n",
    "    return [category_labels[cat] for cat in categories]\n",
    "\n",
    "def dataset_labels(columns):\n",
    "    return [fix_dataset_label(col) for col in columns]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>booking_forms_short_term</th>\n",
       "      <th>booking_forms_medium_term</th>\n",
       "      <th>booking_forms_long_term</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>category</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>active-user</th>\n",
       "      <td>0.046701</td>\n",
       "      <td>0.041571</td>\n",
       "      <td>0.040686</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fair-trial</th>\n",
       "      <td>0.268002</td>\n",
       "      <td>0.020303</td>\n",
       "      <td>0.000271</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>quick-exit</th>\n",
       "      <td>0.232673</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>short-termer</th>\n",
       "      <td>0.290954</td>\n",
       "      <td>0.082213</td>\n",
       "      <td>0.029034</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              booking_forms_short_term  booking_forms_medium_term  \\\n",
       "category                                                            \n",
       "active-user                   0.046701                   0.041571   \n",
       "fair-trial                    0.268002                   0.020303   \n",
       "quick-exit                    0.232673                   0.000000   \n",
       "short-termer                  0.290954                   0.082213   \n",
       "\n",
       "              booking_forms_long_term  \n",
       "category                               \n",
       "active-user                  0.040686  \n",
       "fair-trial                   0.000271  \n",
       "quick-exit                   0.000000  \n",
       "short-termer                 0.029034  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns = ['booking_forms_short_term', 'booking_forms_medium_term', 'booking_forms_long_term']\n",
    "categories = category_labels.keys() # All\n",
    "\n",
    "# Group by category and make sure they're in the correct order\n",
    "df.groupby('category')[columns].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": "# Order categories as defined in category_labels\ncategory_order = [category_labels[k] for k in category_labels.keys()]"
  },
  {
   "cell_type": "code",
   "source": "# Generate charts for all metrics\nmetrics = [\n    'booking_forms',\n    'bookings',\n    'employees', \n    'contacts',\n    'emails',\n    'sms',\n    'appointments',\n    'checklists',\n    'checklists_filled'\n]\n\n# Get total users per category for percentage calculations\ncategory_totals = df.groupby('category').size()\n\ndef create_charts_for_metric(metric_name):\n    cols = [f'{metric_name}_short_term', f'{metric_name}_medium_term', f'{metric_name}_long_term']\n    title_name = metric_name.replace('_', ' ').title()\n    \n    # Chart 1: Average usage\n    grouped = df.groupby('category')[cols].mean().reset_index()\n    melted = grouped.melt(id_vars='category', var_name='timeframe', value_name='value')\n    melted['category_label'] = melted['category'].map(category_labels)\n    \n    fig1 = px.bar(\n        melted,\n        x='category_label',\n        y='value',\n        color='timeframe',\n        barmode='group',\n        title=f'{title_name} Usage by Churn Category and Timeframe',\n        category_orders={'category_label': category_order}\n    )\n    fig1.update_layout(\n        xaxis_title='Category',\n        yaxis_title='Average Usage',\n        legend_title='Timeframe'\n    )\n    fig1.show()\n    \n    # Chart 2: Percentage of users with at least one\n    counts = df.groupby('category')[cols].apply(lambda x: (x > 0).sum()).reset_index()\n    counts_melted = counts.melt(id_vars='category', var_name='timeframe', value_name='count')\n    counts_melted['total'] = counts_melted['category'].map(category_totals)\n    counts_melted['percentage'] = (counts_melted['count'] / counts_melted['total']) * 100\n    counts_melted['category_label'] = counts_melted['category'].map(category_labels)\n    \n    fig2 = px.bar(\n        counts_melted,\n        x='category_label',\n        y='percentage',\n        color='timeframe',\n        barmode='group',\n        title=f'% of Users with At Least One {title_name} by Churn Category and Timeframe',\n        category_orders={'category_label': category_order}\n    )\n    fig2.update_layout(\n        xaxis_title='Category',\n        yaxis_title='% of Users',\n        legend_title='Timeframe'\n    )\n    fig2.show()\n\n# Generate all charts\nfor metric in metrics:\n    create_charts_for_metric(metric)",
   "metadata": {},
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "code",
   "source": "# Generate cumulative charts for all metrics\ndef create_cumulative_charts_for_metric(metric_name):\n    cols = [f'{metric_name}_short_term', f'{metric_name}_medium_term', f'{metric_name}_long_term']\n    title_name = metric_name.replace('_', ' ').title()\n    \n    # Chart 1: Cumulative average usage\n    grouped = df.groupby('category')[cols].mean().reset_index()\n    # Make cumulative\n    grouped['cumulative_short'] = grouped[cols[0]]\n    grouped['cumulative_medium'] = grouped[cols[0]] + grouped[cols[1]]\n    grouped['cumulative_long'] = grouped[cols[0]] + grouped[cols[1]] + grouped[cols[2]]\n    \n    cumulative_cols = ['cumulative_short', 'cumulative_medium', 'cumulative_long']\n    melted = grouped.melt(id_vars='category', value_vars=cumulative_cols, var_name='timeframe', value_name='value')\n    melted['category_label'] = melted['category'].map(category_labels)\n    \n    timeframe_labels_cumulative = {\n        'cumulative_short': 'Through trial',\n        'cumulative_medium': 'Through 90 days',\n        'cumulative_long': 'Through 6 months'\n    }\n    melted['timeframe_label'] = melted['timeframe'].map(timeframe_labels_cumulative)\n    \n    fig1 = px.bar(\n        melted,\n        x='category_label',\n        y='value',\n        color='timeframe_label',\n        barmode='group',\n        title=f'{title_name} Cumulative Usage by Churn Category',\n        category_orders={\n            'category_label': category_order,\n            'timeframe_label': ['Through trial', 'Through 90 days', 'Through 6 months']\n        }\n    )\n    fig1.update_layout(\n        xaxis_title='Category',\n        yaxis_title='Cumulative Average Usage',\n        legend_title='Timeframe'\n    )\n    fig1.show()\n    \n    # Chart 2: Cumulative percentage of users with at least one\n    # Check if user used feature in ANY period up to that point (not sum of counts)\n    df['_cumul_short'] = df[cols[0]] > 0\n    df['_cumul_medium'] = (df[cols[0]] > 0) | (df[cols[1]] > 0)\n    df['_cumul_long'] = (df[cols[0]] > 0) | (df[cols[1]] > 0) | (df[cols[2]] > 0)\n    \n    counts = df.groupby('category')[['_cumul_short', '_cumul_medium', '_cumul_long']].sum().reset_index()\n    counts.columns = ['category', 'cumulative_short', 'cumulative_medium', 'cumulative_long']\n    \n    counts_melted = counts.melt(id_vars='category', value_vars=cumulative_cols, var_name='timeframe', value_name='count')\n    counts_melted['total'] = counts_melted['category'].map(category_totals)\n    counts_melted['percentage'] = (counts_melted['count'] / counts_melted['total']) * 100\n    counts_melted['category_label'] = counts_melted['category'].map(category_labels)\n    counts_melted['timeframe_label'] = counts_melted['timeframe'].map(timeframe_labels_cumulative)\n    \n    fig2 = px.bar(\n        counts_melted,\n        x='category_label',\n        y='percentage',\n        color='timeframe_label',\n        barmode='group',\n        title=f'Cumulative % of Users with At Least One {title_name} by Churn Category',\n        category_orders={\n            'category_label': category_order,\n            'timeframe_label': ['Through trial', 'Through 90 days', 'Through 6 months']\n        }\n    )\n    fig2.update_layout(\n        xaxis_title='Category',\n        yaxis_title='Cumulative % of Users',\n        legend_title='Timeframe'\n    )\n    fig2.show()\n\n# Generate all cumulative charts\nfor metric in metrics:\n    create_cumulative_charts_for_metric(metric)",
   "metadata": {},
   "execution_count": null,
   "outputs": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}