norm/Gainsight
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
e5e1bf3acdbd89c7dab6149f1c0865b08a160a80
Gainsight/Scripts/API_Tests/Untitled1.ipynb

1096 lines
36 KiB
Plaintext
Raw Normal View History

Mostly worked on pandas and jupyter stuff. Made great progress analyzing churned customers.
2023-04-10 16:14:42 -04:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 63,
"id": "c22eadc2",
"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>OrgID</th>\n",
" <th>Organization</th>\n",
" <th>Churn Date</th>\n",
" <th>2022-01</th>\n",
" <th>2022-02</th>\n",
" <th>2022-03</th>\n",
" <th>2022-04</th>\n",
" <th>2022-05</th>\n",
" <th>2022-06</th>\n",
" <th>2022-07</th>\n",
" <th>2022-08</th>\n",
" <th>2022-09</th>\n",
" <th>2022-10</th>\n",
" <th>2022-11</th>\n",
" <th>2022-12</th>\n",
" <th>2023-01</th>\n",
" <th>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>30867753</td>\n",
" <td>Aquent</td>\n",
" <td>2023-04</td>\n",
" <td>58</td>\n",
" <td>38</td>\n",
" <td>50</td>\n",
" <td>50</td>\n",
" <td>39</td>\n",
" <td>36</td>\n",
" <td>46</td>\n",
" <td>46</td>\n",
" <td>43.0</td>\n",
" <td>27.0</td>\n",
" <td>24.0</td>\n",
" <td>26</td>\n",
" <td>22</td>\n",
" <td>8.0</td>\n",
" <td>10.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>33375202</td>\n",
" <td>BioLife Solutions, Inc.</td>\n",
" <td>2023-04</td>\n",
" <td>11</td>\n",
" <td>7</td>\n",
" <td>4</td>\n",
" <td>11</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>30867495</td>\n",
" <td>ZyXel Communications Inc</td>\n",
" <td>2023-04</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>32999202</td>\n",
" <td>BrightLine Eating Solutions LLC</td>\n",
" <td>2023-03</td>\n",
" <td>10,362</td>\n",
" <td>7,890</td>\n",
" <td>7,272</td>\n",
" <td>8,177</td>\n",
" <td>8,468</td>\n",
" <td>7,524</td>\n",
" <td>8,509</td>\n",
" <td>5,638</td>\n",
" <td>581.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>30867752</td>\n",
" <td>Casio America Inc</td>\n",
" <td>2023-03</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OrgID Organization Churn Date 2022-01 2022-02 \n",
"0 30867753 Aquent 2023-04 58 38 \\\n",
"1 33375202 BioLife Solutions, Inc. 2023-04 11 7 \n",
"2 30867495 ZyXel Communications Inc 2023-04 1 1 \n",
"3 32999202 BrightLine Eating Solutions LLC 2023-03 10,362 7,890 \n",
"4 30867752 Casio America Inc 2023-03 NaN NaN \n",
"\n",
" 2022-03 2022-04 2022-05 2022-06 2022-07 2022-08 2022-09 2022-10 2022-11 \n",
"0 50 50 39 36 46 46 43.0 27.0 24.0 \\\n",
"1 4 11 4 NaN NaN NaN NaN NaN NaN \n",
"2 2 1 2 4 2 2 1.0 NaN NaN \n",
"3 7,272 8,177 8,468 7,524 8,509 5,638 581.0 NaN NaN \n",
"4 NaN NaN NaN 1 NaN NaN NaN NaN NaN \n",
"\n",
" 2022-12 2023-01 2023-02 2023-03 2023-04 \n",
"0 26 22 8.0 10.0 2.0 \n",
"1 NaN NaN NaN NaN NaN \n",
"2 NaN NaN 1.0 1.0 NaN \n",
"3 NaN NaN NaN NaN NaN \n",
"4 NaN NaN NaN NaN NaN "
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"import sketch\n",
"import numpy as np\n",
"cd = pd.read_csv(\"/Users/normrasmussen/Downloads/churned_analysis.csv\")\n",
"cd.head()"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "e477c8d4",
"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>OrgID</th>\n",
" <th>Organization</th>\n",
" <th>Churn Date</th>\n",
" <th>2022-01</th>\n",
" <th>2022-02</th>\n",
" <th>2022-03</th>\n",
" <th>2022-04</th>\n",
" <th>2022-05</th>\n",
" <th>2022-06</th>\n",
" <th>2022-07</th>\n",
" <th>2022-08</th>\n",
" <th>2022-09</th>\n",
" <th>2022-10</th>\n",
" <th>2022-11</th>\n",
" <th>2022-12</th>\n",
" <th>2023-01</th>\n",
" <th>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>30867753</td>\n",
" <td>Aquent</td>\n",
" <td>2023-04</td>\n",
" <td>58</td>\n",
" <td>38</td>\n",
" <td>50</td>\n",
" <td>50</td>\n",
" <td>39</td>\n",
" <td>36</td>\n",
" <td>46</td>\n",
" <td>46</td>\n",
" <td>43</td>\n",
" <td>27</td>\n",
" <td>24</td>\n",
" <td>26</td>\n",
" <td>22</td>\n",
" <td>8</td>\n",
" <td>10</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>33375202</td>\n",
" <td>BioLife Solutions Inc.</td>\n",
" <td>2023-04</td>\n",
" <td>11</td>\n",
" <td>7</td>\n",
" <td>4</td>\n",
" <td>11</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>30867495</td>\n",
" <td>ZyXel Communications Inc</td>\n",
" <td>2023-04</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>32999202</td>\n",
" <td>BrightLine Eating Solutions LLC</td>\n",
" <td>2023-03</td>\n",
" <td>10362</td>\n",
" <td>7890</td>\n",
" <td>7272</td>\n",
" <td>8177</td>\n",
" <td>8468</td>\n",
" <td>7524</td>\n",
" <td>8509</td>\n",
" <td>5638</td>\n",
" <td>581</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>30867752</td>\n",
" <td>Casio America Inc</td>\n",
" <td>2023-03</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OrgID Organization Churn Date 2022-01 2022-02 \n",
"0 30867753 Aquent 2023-04 58 38 \\\n",
"1 33375202 BioLife Solutions Inc. 2023-04 11 7 \n",
"2 30867495 ZyXel Communications Inc 2023-04 1 1 \n",
"3 32999202 BrightLine Eating Solutions LLC 2023-03 10362 7890 \n",
"4 30867752 Casio America Inc 2023-03 0 0 \n",
"\n",
" 2022-03 2022-04 2022-05 2022-06 2022-07 2022-08 2022-09 2022-10 \n",
"0 50 50 39 36 46 46 43 27 \\\n",
"1 4 11 4 0 0 0 0 0 \n",
"2 2 1 2 4 2 2 1 0 \n",
"3 7272 8177 8468 7524 8509 5638 581 0 \n",
"4 0 0 0 1 0 0 0 0 \n",
"\n",
" 2022-11 2022-12 2023-01 2023-02 2023-03 2023-04 \n",
"0 24 26 22 8 10 2 \n",
"1 0 0 0 0 0 0 \n",
"2 0 0 0 1 1 0 \n",
"3 0 0 0 0 0 0 \n",
"4 0 0 0 0 0 0 "
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Replace all NaN values with 0\n",
"cd.fillna(0, inplace=True)\n",
"cd.replace(np.inf, 0)\n",
"\n",
"# Remove all commas from strings\n",
"cd.replace(',','', regex=True, inplace=True)\n",
"\n",
"# Convert all strings after the column 'Churn Data' to integers\n",
"for col in cd.columns[4:]:\n",
" cd[col] = cd[col].astype(int)\n",
"\n",
"cd.head()"
]
},
{
"cell_type": "code",
"execution_count": 65,
"id": "06f9cb22",
"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>2022-01</th>\n",
" <th>2022-02</th>\n",
" <th>2022-03</th>\n",
" <th>2022-04</th>\n",
" <th>2022-05</th>\n",
" <th>2022-06</th>\n",
" <th>2022-07</th>\n",
" <th>2022-08</th>\n",
" <th>2022-09</th>\n",
" <th>2022-10</th>\n",
" <th>2022-11</th>\n",
" <th>2022-12</th>\n",
" <th>2023-01</th>\n",
" <th>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>58</td>\n",
" <td>38</td>\n",
" <td>50</td>\n",
" <td>50</td>\n",
" <td>39</td>\n",
" <td>36</td>\n",
" <td>46</td>\n",
" <td>46</td>\n",
" <td>43</td>\n",
" <td>27</td>\n",
" <td>24</td>\n",
" <td>26</td>\n",
" <td>22</td>\n",
" <td>8</td>\n",
" <td>10</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>11</td>\n",
" <td>7</td>\n",
" <td>4</td>\n",
" <td>11</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>10362</td>\n",
" <td>7890</td>\n",
" <td>7272</td>\n",
" <td>8177</td>\n",
" <td>8468</td>\n",
" <td>7524</td>\n",
" <td>8509</td>\n",
" <td>5638</td>\n",
" <td>581</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>81</td>\n",
" <td>19</td>\n",
" <td>51</td>\n",
" <td>26</td>\n",
" <td>26</td>\n",
" <td>32</td>\n",
" <td>79</td>\n",
" <td>68</td>\n",
" <td>35</td>\n",
" <td>23</td>\n",
" <td>33</td>\n",
" <td>25</td>\n",
" <td>75</td>\n",
" <td>71</td>\n",
" <td>29</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>19</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>386</td>\n",
" <td>378</td>\n",
" <td>396</td>\n",
" <td>732</td>\n",
" <td>947</td>\n",
" <td>762</td>\n",
" <td>1203</td>\n",
" <td>889</td>\n",
" <td>438</td>\n",
" <td>178</td>\n",
" <td>115</td>\n",
" <td>214</td>\n",
" <td>92</td>\n",
" <td>165</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>7</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>63</td>\n",
" <td>15</td>\n",
" <td>10</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>28</td>\n",
" <td>27</td>\n",
" <td>79</td>\n",
" <td>17</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>8</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>2</td>\n",
" <td>37</td>\n",
" <td>19</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>38</td>\n",
" <td>24</td>\n",
" <td>6</td>\n",
" <td>21</td>\n",
" <td>35</td>\n",
" <td>10</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>22</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>381</td>\n",
" <td>677</td>\n",
" <td>583</td>\n",
" <td>671</td>\n",
" <td>515</td>\n",
" <td>380</td>\n",
" <td>181</td>\n",
" <td>449</td>\n",
" <td>12</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>721</td>\n",
" <td>775</td>\n",
" <td>825</td>\n",
" <td>606</td>\n",
" <td>578</td>\n",
" <td>501</td>\n",
" <td>497</td>\n",
" <td>543</td>\n",
" <td>628</td>\n",
" <td>505</td>\n",
" <td>650</td>\n",
" <td>1270</td>\n",
" <td>1957</td>\n",
" <td>190</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>8</td>\n",
" <td>7</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>10</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>2766</td>\n",
" <td>2895</td>\n",
" <td>2633</td>\n",
" <td>2378</td>\n",
" <td>2263</td>\n",
" <td>2143</td>\n",
" <td>2060</td>\n",
" <td>587</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>9</td>\n",
" <td>18</td>\n",
" <td>33</td>\n",
" <td>8</td>\n",
" <td>8</td>\n",
" <td>5</td>\n",
" <td>13</td>\n",
" <td>28</td>\n",
" <td>14</td>\n",
" <td>15</td>\n",
" <td>6</td>\n",
" <td>13</td>\n",
" <td>6</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>126</td>\n",
" <td>158</td>\n",
" <td>136</td>\n",
" <td>64</td>\n",
" <td>75</td>\n",
" <td>96</td>\n",
" <td>83</td>\n",
" <td>63</td>\n",
" <td>38</td>\n",
" <td>13</td>\n",
" <td>10</td>\n",
" <td>14</td>\n",
" <td>13</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>404</td>\n",
" <td>424</td>\n",
" <td>334</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>13</td>\n",
" <td>10</td>\n",
" <td>6</td>\n",
" <td>3</td>\n",
" <td>7</td>\n",
" <td>21</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>20</td>\n",
" <td>197</td>\n",
" <td>24</td>\n",
" <td>9</td>\n",
" <td>23</td>\n",
" <td>21</td>\n",
" <td>38</td>\n",
" <td>15</td>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>29</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>9</td>\n",
" <td>12</td>\n",
" <td>20</td>\n",
" <td>4</td>\n",
" <td>38</td>\n",
" <td>10</td>\n",
" <td>7</td>\n",
" <td>15</td>\n",
" <td>99</td>\n",
" <td>128</td>\n",
" <td>11</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 2022-01 2022-02 2022-03 2022-04 2022-05 2022-06 2022-07 2022-08 \n",
"0 58 38 50 50 39 36 46 46 \\\n",
"1 11 7 4 11 4 0 0 0 \n",
"2 1 1 2 1 2 4 2 2 \n",
"3 10362 7890 7272 8177 8468 7524 8509 5638 \n",
"4 0 0 0 0 0 1 0 0 \n",
"5 81 19 51 26 26 32 79 68 \n",
"6 0 0 0 0 0 4 1 0 \n",
"7 386 378 396 732 947 762 1203 889 \n",
"8 0 1 1 2 7 5 4 5 \n",
"9 63 15 10 4 8 2 3 0 \n",
"10 28 27 79 17 1 3 8 0 \n",
"11 2 37 19 2 1 38 24 6 \n",
"12 0 1 4 22 2 1 7 0 \n",
"13 381 677 583 671 515 380 181 449 \n",
"14 721 775 825 606 578 501 497 543 \n",
"15 0 5 5 20 8 7 4 3 \n",
"16 2766 2895 2633 2378 2263 2143 2060 587 \n",
"17 0 0 0 0 0 0 0 0 \n",
"18 0 1 2 2 0 1 2 0 \n",
"19 9 18 33 8 8 5 13 28 \n",
"20 126 158 136 64 75 96 83 63 \n",
"21 4 2 1 0 0 0 0 0 \n",
"22 404 424 334 0 0 0 0 0 \n",
"23 13 10 6 3 7 21 2 5 \n",
"24 0 0 0 0 0 0 0 0 \n",
"25 20 197 24 9 23 21 38 15 \n",
"26 29 5 7 9 12 20 4 38 \n",
"\n",
" 2022-09 2022-10 2022-11 2022-12 2023-01 2023-02 2023-03 2023-04 \n",
"0 43 27 24 26 22 8 10 2 \n",
"1 0 0 0 0 0 0 0 0 \n",
"2 1 0 0 0 0 1 1 0 \n",
"3 581 0 0 0 0 0 0 0 \n",
"4 0 0 0 0 0 0 0 0 \n",
"5 35 23 33 25 75 71 29 4 \n",
"6 0 0 0 19 3 0 0 0 \n",
"7 438 178 115 214 92 165 0 0 \n",
"8 6 6 0 0 0 0 0 0 \n",
"9 4 4 6 5 5 2 0 0 \n",
"10 1 0 1 1 2 0 0 0 \n",
"11 21 35 10 7 1 0 0 0 \n",
"12 0 0 0 2 0 2 0 0 \n",
"13 12 0 1 1 1 0 0 0 \n",
"14 628 505 650 1270 1957 190 0 0 \n",
"15 4 0 10 9 0 1 0 0 \n",
"16 0 0 0 0 0 0 0 0 \n",
"17 0 0 0 0 0 0 0 0 \n",
"18 2 1 2 0 1 0 0 0 \n",
"19 14 15 6 13 6 2 0 0 \n",
"20 38 13 10 14 13 3 0 0 \n",
"21 0 0 0 0 1 0 0 0 \n",
"22 0 0 0 0 0 0 0 0 \n",
"23 8 5 4 8 2 2 0 0 \n",
"24 0 0 0 0 0 1 1 0 \n",
"25 4 10 2 3 4 4 0 0 \n",
"26 10 7 15 99 128 11 0 0 "
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create a copy of the dataframe\n",
"cd_scaled = cd.copy()\n",
"cd_scaled = cd_scaled.drop(['Organization', 'Churn Date', 'OrgID'], axis=1)\n",
"cd_scaled.head(100)"
]
},
{
"cell_type": "code",
"execution_count": 66,
"id": "af57bdc4",
"metadata": {},
"outputs": [
{
"ename": "ZeroDivisionError",
"evalue": "division by zero",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mZeroDivisionError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[66], line 9\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[38;5;66;03m# Scale each value in the row using min-max scaling\u001b[39;00m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m col \u001b[38;5;129;01min\u001b[39;00m row[\u001b[38;5;241m2\u001b[39m:]:\n\u001b[0;32m----> 9\u001b[0m cd_scaled\u001b[38;5;241m.\u001b[39mloc[index, col] \u001b[38;5;241m=\u001b[39m \u001b[43m(\u001b[49m\u001b[43mcol\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmin_val\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m/\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mmax_val\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmin_val\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[0;31mZeroDivisionError\u001b[0m: division by zero"
]
}
],
"source": [
"# Iterate over each row in the dataframe\n",
"for index, row in cd_scaled.iterrows():\n",
" # Get the min and max values for the row\n",
" min_val = int(row[1:].min())\n",
" max_val = int(row[1:].max())\n",
"\n",
" # Scale each value in the row using min-max scaling\n",
" for col in row[2:]:\n",
" cd_scaled.loc[index, col] = (col - min_val) / (max_val - min_val)"
]
}
],
"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": "3.11.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink