{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "74c4f75e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import boto3\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b472f341",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ec2-user/anaconda3/envs/python3/lib/python3.10/site-packages/fsspec/registry.py:279: UserWarning: Your installed version of s3fs is very old and known to cause\n",
      "severe performance issues, see also https://github.com/dask/dask/issues/10276\n",
      "\n",
      "To fix, you should specify a lower version bound on s3fs, or\n",
      "update the current installation.\n",
      "\n",
      "  warnings.warn(s3_msg)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(5205200, 8)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('s3://dev-cucumbers/eimpara/pipelines/moments/fourier_table_20240812_one_script_test_merged.csv')\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "268670cf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1022140, 8)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sub = pd.read_csv('s3://dev-cucumbers/eimpara/pipelines/moments/fourier_table_subset_inflection_last_7_days_20240812_one_script_test_merged.csv')\n",
    "sub.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a6e6f33a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['ACTIVITY_DATE', 'Fourier', 'Fourier_real_part', 'ISRC', 'ISRC_KEY',\n",
       "       'Inflection_Point', 'STREAMS', 'TRANSACTION_COUNTRY_CODE'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sub.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "06bf8cb2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7301"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sub['ISRC_KEY'].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "edcc4f22",
   "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>TRANSACTION_COUNTRY_CODE</th>\n",
       "      <th>ISRC_KEY</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DE</td>\n",
       "      <td>168560</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ES</td>\n",
       "      <td>151900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>FR</td>\n",
       "      <td>147420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>GB</td>\n",
       "      <td>167860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IT</td>\n",
       "      <td>143500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>US</td>\n",
       "      <td>200480</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>WW</td>\n",
       "      <td>42420</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  TRANSACTION_COUNTRY_CODE  ISRC_KEY\n",
       "0                       DE    168560\n",
       "1                       ES    151900\n",
       "2                       FR    147420\n",
       "3                       GB    167860\n",
       "4                       IT    143500\n",
       "5                       US    200480\n",
       "6                       WW     42420"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp = sub.groupby('TRANSACTION_COUNTRY_CODE')['ISRC_KEY'].count().reset_index()\n",
    "grp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "62383bea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1085.0"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "151900/140"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "84dd61f6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}