394 lines
14 KiB
Plaintext
394 lines
14 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os\n",
|
||
"import sys\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import seaborn as sns\n",
|
||
"\n",
|
||
"nb_dir = os.path.split(os.getcwd())[0]\n",
|
||
"if nb_dir not in sys.path:\n",
|
||
" sys.path.append(nb_dir)\n",
|
||
" \n",
|
||
"from features.communication import *\n",
|
||
"import participants.query_db\n",
|
||
"\n",
|
||
"participants_inactive_usernames = participants.query_db.get_usernames()\n",
|
||
"df_sms = get_sms_data(participants_inactive_usernames)\n",
|
||
"df_calls = get_call_data(participants_inactive_usernames)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
" count_calls = count_comms(df_calls)\n",
|
||
" count_sms = count_comms(df_sms)\n",
|
||
"\n",
|
||
" count_joined = count_calls.merge(\n",
|
||
" count_sms, on=\"participant_id\", suffixes=(\"_calls\", \"_sms\")\n",
|
||
" )"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"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>participant_id</th>\n",
|
||
" <th>no_incoming</th>\n",
|
||
" <th>no_outgoing</th>\n",
|
||
" <th>no_missed</th>\n",
|
||
" <th>no_all_calls</th>\n",
|
||
" <th>no_incoming_ratio</th>\n",
|
||
" <th>no_outgoing_ratio</th>\n",
|
||
" <th>duration_total_incoming</th>\n",
|
||
" <th>duration_total_outgoing</th>\n",
|
||
" <th>duration_max_incoming</th>\n",
|
||
" <th>duration_max_outgoing</th>\n",
|
||
" <th>no_received</th>\n",
|
||
" <th>no_sent</th>\n",
|
||
" <th>no_all_sms</th>\n",
|
||
" <th>no_received_ratio</th>\n",
|
||
" <th>no_sent_ratio</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>13</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>21.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>26.0</td>\n",
|
||
" <td>0.115385</td>\n",
|
||
" <td>0.807692</td>\n",
|
||
" <td>342.0</td>\n",
|
||
" <td>2836.0</td>\n",
|
||
" <td>196.0</td>\n",
|
||
" <td>355.0</td>\n",
|
||
" <td>7.0</td>\n",
|
||
" <td>7.0</td>\n",
|
||
" <td>14.0</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>14</td>\n",
|
||
" <td>16.0</td>\n",
|
||
" <td>22.0</td>\n",
|
||
" <td>11.0</td>\n",
|
||
" <td>49.0</td>\n",
|
||
" <td>0.326531</td>\n",
|
||
" <td>0.448980</td>\n",
|
||
" <td>1873.0</td>\n",
|
||
" <td>2789.0</td>\n",
|
||
" <td>346.0</td>\n",
|
||
" <td>694.0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" <td>14.0</td>\n",
|
||
" <td>34.0</td>\n",
|
||
" <td>0.588235</td>\n",
|
||
" <td>0.411765</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>15</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>5.0</td>\n",
|
||
" <td>0.600000</td>\n",
|
||
" <td>0.400000</td>\n",
|
||
" <td>310.0</td>\n",
|
||
" <td>19.0</td>\n",
|
||
" <td>154.0</td>\n",
|
||
" <td>19.0</td>\n",
|
||
" <td>73.0</td>\n",
|
||
" <td>73.0</td>\n",
|
||
" <td>146.0</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>16</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>6.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>13.0</td>\n",
|
||
" <td>0.307692</td>\n",
|
||
" <td>0.461538</td>\n",
|
||
" <td>1963.0</td>\n",
|
||
" <td>849.0</td>\n",
|
||
" <td>1037.0</td>\n",
|
||
" <td>638.0</td>\n",
|
||
" <td>8.0</td>\n",
|
||
" <td>2.0</td>\n",
|
||
" <td>10.0</td>\n",
|
||
" <td>0.800000</td>\n",
|
||
" <td>0.200000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>17</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" <td>60.0</td>\n",
|
||
" <td>8.0</td>\n",
|
||
" <td>88.0</td>\n",
|
||
" <td>0.227273</td>\n",
|
||
" <td>0.681818</td>\n",
|
||
" <td>5789.0</td>\n",
|
||
" <td>17046.0</td>\n",
|
||
" <td>1966.0</td>\n",
|
||
" <td>3830.0</td>\n",
|
||
" <td>7.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>8.0</td>\n",
|
||
" <td>0.875000</td>\n",
|
||
" <td>0.125000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>56</th>\n",
|
||
" <td>91</td>\n",
|
||
" <td>15.0</td>\n",
|
||
" <td>13.0</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>31.0</td>\n",
|
||
" <td>0.483871</td>\n",
|
||
" <td>0.419355</td>\n",
|
||
" <td>3443.0</td>\n",
|
||
" <td>3636.0</td>\n",
|
||
" <td>644.0</td>\n",
|
||
" <td>1315.0</td>\n",
|
||
" <td>83.0</td>\n",
|
||
" <td>44.0</td>\n",
|
||
" <td>127.0</td>\n",
|
||
" <td>0.653543</td>\n",
|
||
" <td>0.346457</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>57</th>\n",
|
||
" <td>92</td>\n",
|
||
" <td>3.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>1.0</td>\n",
|
||
" <td>8.0</td>\n",
|
||
" <td>0.375000</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" <td>231.0</td>\n",
|
||
" <td>648.0</td>\n",
|
||
" <td>167.0</td>\n",
|
||
" <td>433.0</td>\n",
|
||
" <td>4.0</td>\n",
|
||
" <td>6.0</td>\n",
|
||
" <td>10.0</td>\n",
|
||
" <td>0.400000</td>\n",
|
||
" <td>0.600000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>58</th>\n",
|
||
" <td>93</td>\n",
|
||
" <td>22.0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" <td>9.0</td>\n",
|
||
" <td>51.0</td>\n",
|
||
" <td>0.431373</td>\n",
|
||
" <td>0.392157</td>\n",
|
||
" <td>2534.0</td>\n",
|
||
" <td>1444.0</td>\n",
|
||
" <td>443.0</td>\n",
|
||
" <td>672.0</td>\n",
|
||
" <td>48.0</td>\n",
|
||
" <td>19.0</td>\n",
|
||
" <td>67.0</td>\n",
|
||
" <td>0.716418</td>\n",
|
||
" <td>0.283582</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>59</th>\n",
|
||
" <td>106</td>\n",
|
||
" <td>12.0</td>\n",
|
||
" <td>30.0</td>\n",
|
||
" <td>6.0</td>\n",
|
||
" <td>48.0</td>\n",
|
||
" <td>0.250000</td>\n",
|
||
" <td>0.625000</td>\n",
|
||
" <td>3049.0</td>\n",
|
||
" <td>2637.0</td>\n",
|
||
" <td>878.0</td>\n",
|
||
" <td>380.0</td>\n",
|
||
" <td>10.0</td>\n",
|
||
" <td>10.0</td>\n",
|
||
" <td>20.0</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" <td>0.500000</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>60</th>\n",
|
||
" <td>107</td>\n",
|
||
" <td>11.0</td>\n",
|
||
" <td>42.0</td>\n",
|
||
" <td>13.0</td>\n",
|
||
" <td>66.0</td>\n",
|
||
" <td>0.166667</td>\n",
|
||
" <td>0.636364</td>\n",
|
||
" <td>3804.0</td>\n",
|
||
" <td>9977.0</td>\n",
|
||
" <td>1519.0</td>\n",
|
||
" <td>1943.0</td>\n",
|
||
" <td>80.0</td>\n",
|
||
" <td>176.0</td>\n",
|
||
" <td>256.0</td>\n",
|
||
" <td>0.312500</td>\n",
|
||
" <td>0.687500</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>61 rows × 16 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" participant_id no_incoming no_outgoing no_missed no_all_calls \\\n",
|
||
"0 13 3.0 21.0 2.0 26.0 \n",
|
||
"1 14 16.0 22.0 11.0 49.0 \n",
|
||
"2 15 3.0 2.0 NaN 5.0 \n",
|
||
"3 16 4.0 6.0 3.0 13.0 \n",
|
||
"4 17 20.0 60.0 8.0 88.0 \n",
|
||
".. ... ... ... ... ... \n",
|
||
"56 91 15.0 13.0 3.0 31.0 \n",
|
||
"57 92 3.0 4.0 1.0 8.0 \n",
|
||
"58 93 22.0 20.0 9.0 51.0 \n",
|
||
"59 106 12.0 30.0 6.0 48.0 \n",
|
||
"60 107 11.0 42.0 13.0 66.0 \n",
|
||
"\n",
|
||
" no_incoming_ratio no_outgoing_ratio duration_total_incoming \\\n",
|
||
"0 0.115385 0.807692 342.0 \n",
|
||
"1 0.326531 0.448980 1873.0 \n",
|
||
"2 0.600000 0.400000 310.0 \n",
|
||
"3 0.307692 0.461538 1963.0 \n",
|
||
"4 0.227273 0.681818 5789.0 \n",
|
||
".. ... ... ... \n",
|
||
"56 0.483871 0.419355 3443.0 \n",
|
||
"57 0.375000 0.500000 231.0 \n",
|
||
"58 0.431373 0.392157 2534.0 \n",
|
||
"59 0.250000 0.625000 3049.0 \n",
|
||
"60 0.166667 0.636364 3804.0 \n",
|
||
"\n",
|
||
" duration_total_outgoing duration_max_incoming duration_max_outgoing \\\n",
|
||
"0 2836.0 196.0 355.0 \n",
|
||
"1 2789.0 346.0 694.0 \n",
|
||
"2 19.0 154.0 19.0 \n",
|
||
"3 849.0 1037.0 638.0 \n",
|
||
"4 17046.0 1966.0 3830.0 \n",
|
||
".. ... ... ... \n",
|
||
"56 3636.0 644.0 1315.0 \n",
|
||
"57 648.0 167.0 433.0 \n",
|
||
"58 1444.0 443.0 672.0 \n",
|
||
"59 2637.0 878.0 380.0 \n",
|
||
"60 9977.0 1519.0 1943.0 \n",
|
||
"\n",
|
||
" no_received no_sent no_all_sms no_received_ratio no_sent_ratio \n",
|
||
"0 7.0 7.0 14.0 0.500000 0.500000 \n",
|
||
"1 20.0 14.0 34.0 0.588235 0.411765 \n",
|
||
"2 73.0 73.0 146.0 0.500000 0.500000 \n",
|
||
"3 8.0 2.0 10.0 0.800000 0.200000 \n",
|
||
"4 7.0 1.0 8.0 0.875000 0.125000 \n",
|
||
".. ... ... ... ... ... \n",
|
||
"56 83.0 44.0 127.0 0.653543 0.346457 \n",
|
||
"57 4.0 6.0 10.0 0.400000 0.600000 \n",
|
||
"58 48.0 19.0 67.0 0.716418 0.283582 \n",
|
||
"59 10.0 10.0 20.0 0.500000 0.500000 \n",
|
||
"60 80.0 176.0 256.0 0.312500 0.687500 \n",
|
||
"\n",
|
||
"[61 rows x 16 columns]"
|
||
]
|
||
},
|
||
"execution_count": 9,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"count_joined.reset_index()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "straw2analysis",
|
||
"language": "python",
|
||
"name": "straw2analysis"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.9.6"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|