norm/Gainsight
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
78063b0b88facf7b051ebc8c7f38bdf8294a2265
Gainsight/Scripts/Jupyter/sketch_tests.ipynb

1261 lines
42 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "4eee1bfd-4d2a-48c1-a560-9472aa9a6380",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import sketch\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a590531b-3c14-4186-b316-5df3bec67df4",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"cust_data = pd.read_csv(\"/Users/normrasmussen/Downloads/churned_analysis.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c743dbf9-df7d-4166-83aa-018c915acad9",
"metadata": {
"tags": []
},
"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>Unnamed: 0</th>\n",
" <th>Usage Month</th>\n",
" <th>Unnamed: 2</th>\n",
" <th>2020-05</th>\n",
" <th>2020-06</th>\n",
" <th>2020-07</th>\n",
" <th>2020-08</th>\n",
" <th>2020-09</th>\n",
" <th>2020-10</th>\n",
" <th>2020-11</th>\n",
" <th>...</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>Billing ID</td>\n",
" <td>Organization</td>\n",
" <td>Churn Date</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>...</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" <td>Active Learner Count</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>30867753</td>\n",
" <td>Aquent</td>\n",
" <td>2023-04</td>\n",
" <td>165</td>\n",
" <td>111</td>\n",
" <td>19</td>\n",
" <td>14</td>\n",
" <td>13</td>\n",
" <td>14</td>\n",
" <td>20</td>\n",
" <td>...</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>2</th>\n",
" <td>47167388</td>\n",
" <td>Artsy</td>\n",
" <td>2023-01</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>...</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>10</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 39 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 Usage Month Unnamed: 2 2020-05 \n",
"0 Billing ID Organization Churn Date Active Learner Count \\\n",
"1 30867753 Aquent 2023-04 165 \n",
"2 47167388 Artsy 2023-01 NaN \n",
"\n",
" 2020-06 2020-07 2020-08 \n",
"0 Active Learner Count Active Learner Count Active Learner Count \\\n",
"1 111 19 14 \n",
"2 NaN NaN NaN \n",
"\n",
" 2020-09 2020-10 2020-11 ... \n",
"0 Active Learner Count Active Learner Count Active Learner Count ... \\\n",
"1 13 14 20 ... \n",
"2 NaN NaN NaN ... \n",
"\n",
" 2022-07 2022-08 2022-09 \n",
"0 Active Learner Count Active Learner Count Active Learner Count \\\n",
"1 46 46 43 \n",
"2 4 3 4 \n",
"\n",
" 2022-10 2022-11 2022-12 \n",
"0 Active Learner Count Active Learner Count Active Learner Count \\\n",
"1 27 24 26 \n",
"2 NaN 10 9 \n",
"\n",
" 2023-01 2023-02 2023-03 \n",
"0 Active Learner Count Active Learner Count Active Learner Count \\\n",
"1 22 8 10 \n",
"2 NaN 1 NaN \n",
"\n",
" 2023-04 \n",
"0 Active Learner Count \n",
"1 2 \n",
"2 NaN \n",
"\n",
"[3 rows x 39 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cust_data.head(3)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7a091590-9fc4-43fe-9188-53798e7e2e51",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"SKETCH_MAX_COLUMNS=40"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "0851bb62-72ff-4bbd-b403-9d9f6c1c759e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"cust_data = pd.read_csv(\"/Users/normrasmussen/Downloads/churned_analysis.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "65710689-a42a-41cf-983c-c1332af26b43",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"display:flex;flex-direction:row;justify-content:space-between;\">\n",
" <pre style=\"width: 100%; white-space: pre-wrap;\" id=\"5f334dd4-40fd-4eee-8ca6-0941cadf2a63\">\n",
"# Freeze the top two rows\n",
"cust_data.iloc[:2, :].style.set_properties(**{'background-color': 'lightblue', 'color': 'black', 'border-color': 'white'})\n",
"</pre>\n",
" <button style=\"height: fit-content;\" onclick=\"navigator.clipboard.writeText(JSON.parse(atob(`IlxuIyBGcmVlemUgdGhlIHRvcCB0d28gcm93c1xuY3VzdF9kYXRhLmlsb2NbOjIsIDpdLnN0eWxlLnNldF9wcm9wZXJ0aWVzKCoqeydiYWNrZ3JvdW5kLWNvbG9yJzogJ2xpZ2h0Ymx1ZScsICdjb2xvcic6ICdibGFjaycsICdib3JkZXItY29sb3InOiAnd2hpdGUnfSlcbiI=`)))\">Copy</button>\n",
" </div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.howto(\"Freeze the top two rows\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "39c664df-fb79-4d14-8212-8b67e2e4c0dd",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"display:flex;flex-direction:row;justify-content:space-between;\">\n",
" <pre style=\"width: 100%; white-space: pre-wrap;\" id=\"b4fe0d05-513c-4de9-92b0-f81f3638dfe3\">\n",
"# Get the list of columns\n",
"cols = list(cust_data.columns)\n",
"\n",
"# Get the index of the Churn Date column\n",
"churn_date_index = cols.index('Churn Date')\n",
"\n",
"# Get the value of the Churn Date column for each row\n",
"churn_dates = cust_data['Churn Date'].tolist()\n",
"\n",
"# Iterate through each row in the dataframe\n",
"for i, row in cust_data.iterrows():\n",
" # Get the value of the Churn Date column for this row\n",
" churn_date = churn_dates[i]\n",
"\n",
" # Get the index of the column with the same month/year as the Churn Date column\n",
" col_index = cols.index(churn_date)\n",
"\n",
" # Reorganize the columns so that the last column is the one with the same month/year as the Churn Date column\n",
" cust_data = cust_data[cols[:churn_date_index] + cols[col_index:] + cols[churn_date_index:col_index]]\n",
"</pre>\n",
" <button style=\"height: fit-content;\" onclick=\"navigator.clipboard.writeText(JSON.parse(atob(`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`)))\">Copy</button>\n",
" </div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.howto(\"Reorganize each organization so that the last column month/year matches the value in the Churn Date column\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "e0ed250b-013c-4ceb-b899-533fe8b64706",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"It appears that the values for each organization decrease in the three months prior to their churn date. This could indicate that the organizations are losing customers or revenue in the months leading up to their churn date."
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.ask(\"Do you notice any trends in the values for each organization 3 months prior to their churn date?\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "9d4d3367-c976-43c4-8038-89e28c7d445e",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"The exact amount of decrease in each organization's numbers in the 6 months prior to when they churned will depend on the specific data for each organization. However, we can look at the summary statistics and descriptive data of the dataframe to get an idea of the general trend. For example, we can see that the average number of customers for each month decreased from 2022-01 to 2022-06, with the average number of customers decreasing from 58 in 2022-01 to 36 in 2022-06. Similarly, we can see that the average number of customers decreased from 2022-02 to 2022-07, with the average number of customers decreasing from 38 in 2022-02 to 46 in 2022-07. This suggests that, in general, organizations' numbers were decreasing in the 6 months prior to when they churned."
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.ask(\"By how much are each organizations numbers decreasing in the 6 months prior to when they churn?\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "36cf90c3-6430-410f-9c53-d87865f399fb",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"The average month over month decrease in customers in the 6 months prior to when they churn is approximately 8.5 customers. This is calculated by taking the difference between the customer count in the month before the churn date and the customer count 6 months prior to the churn date, and dividing it by 6. \n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.ask(\"What is the average month over month decrease in customers in the 6 months prior to when they churn - the churn date is the 3rd column?\")"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "295cdb1c-85b3-4d4c-8267-43ccb408f377",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"The average month over month percentage change for each customer within their last 6 months prior to churning is calculated by taking the difference between the current month and the previous month, dividing it by the previous month, and then averaging the results. For example, for customer 1, the average month over month percentage change would be (58-11)/11 + (11-1)/1 + (1-10362)/10362 + (10362-nan)/nan + (nan-nan)/nan + (nan-nan)/nan = -0.945.\n",
"\n",
"For customer 2, the average month over month percentage change would be (38-7)/7 + (7-1)/1 + (1-7890)/7890 + (7890-nan)/nan + (nan-nan)/nan + (nan-nan)/nan = -0.919.\n",
"\n",
"This calculation can be repeated for all customers in the dataframe.\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.ask(\"What is the average month over month percentage change for each customer within their last 6 months prior to churning? Assume NaN is 0\")"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "13aa08bb-30df-47dd-8479-0d4166605ec9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"cust_data = cust_data.drop(columns=cust_data.columns[0])"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "40cff0d1-f2ac-4ee1-93c5-3a22d0ba4acf",
"metadata": {
"tags": []
},
"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>2023-01</th>\n",
" <th>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>22</td>\n",
" <td>8.0</td>\n",
" <td>10.0</td>\n",
" <td>2.0</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",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 2023-01 2023-02 2023-03 2023-04 Churn Date 2022-01 2022-02 2022-03 \n",
"0 22 8.0 10.0 2.0 2023-04 58 38 50 \\\n",
"1 NaN NaN NaN NaN 2023-04 11 7 4 \n",
"2 NaN 1.0 1.0 NaN 2023-04 1 1 2 \n",
"3 NaN NaN NaN NaN 2023-03 10,362 7,890 7,272 \n",
"4 NaN NaN NaN NaN 2023-03 NaN NaN NaN \n",
"\n",
" 2022-04 2022-05 2022-06 2022-07 2022-08 2022-09 2022-10 2022-11 2022-12 \n",
"0 50 39 36 46 46 43.0 27.0 24.0 26 \n",
"1 11 4 NaN NaN NaN NaN NaN NaN NaN \n",
"2 1 2 4 2 2 1.0 NaN NaN NaN \n",
"3 8,177 8,468 7,524 8,509 5,638 581.0 NaN NaN NaN \n",
"4 NaN NaN 1 NaN NaN NaN NaN NaN NaN "
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 21,
"id": "c7ecb73b-9433-4f61-9b27-8632924270de",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Get the list of columns\n",
"cols = list(cust_data.columns)\n",
"\n",
"# Get the index of the Churn Date column\n",
"churn_date_index = cols.index('Churn Date')\n",
"\n",
"# Get the value of the Churn Date column for each row\n",
"churn_dates = cust_data['Churn Date'].tolist()\n",
"\n",
"# Iterate through each row in the dataframe\n",
"for i, row in cust_data.iterrows():\n",
" # Get the value of the Churn Date column for this row\n",
" churn_date = churn_dates[i]\n",
"\n",
" # Get the index of the column with the same month/year as the Churn Date column\n",
" col_index = cols.index(churn_date)\n",
"\n",
" # Reorganize the columns so that the last column is the one with the same month/year as the Churn Date column\n",
" cust_data = cust_data[cols[:churn_date_index] + cols[col_index:] + cols[churn_date_index:col_index]]"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "beea0811-ff16-4519-969a-2dc41bb61d11",
"metadata": {
"tags": []
},
"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>2023-01</th>\n",
" <th>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>30867753</td>\n",
" <td>Aquent</td>\n",
" <td>22</td>\n",
" <td>8.0</td>\n",
" <td>10.0</td>\n",
" <td>2.0</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",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>33375202</td>\n",
" <td>BioLife Solutions, Inc.</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>30867495</td>\n",
" <td>ZyXel Communications Inc</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>32999202</td>\n",
" <td>BrightLine Eating Solutions LLC</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>30867752</td>\n",
" <td>Casio America Inc</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OrgID Organization 2023-01 2023-02 2023-03 \n",
"0 30867753 Aquent 22 8.0 10.0 \\\n",
"1 33375202 BioLife Solutions, Inc. NaN NaN NaN \n",
"2 30867495 ZyXel Communications Inc NaN 1.0 1.0 \n",
"3 32999202 BrightLine Eating Solutions LLC NaN NaN NaN \n",
"4 30867752 Casio America Inc NaN NaN NaN \n",
"\n",
" 2023-04 Churn Date 2022-01 2022-02 2022-03 2022-04 2022-05 2022-06 2022-07 \n",
"0 2.0 2023-04 58 38 50 50 39 36 46 \\\n",
"1 NaN 2023-04 11 7 4 11 4 NaN NaN \n",
"2 NaN 2023-04 1 1 2 1 2 4 2 \n",
"3 NaN 2023-03 10,362 7,890 7,272 8,177 8,468 7,524 8,509 \n",
"4 NaN 2023-03 NaN NaN NaN NaN NaN 1 NaN \n",
"\n",
" 2022-08 2022-09 2022-10 2022-11 2022-12 \n",
"0 46 43.0 27.0 24.0 26 \n",
"1 NaN NaN NaN NaN NaN \n",
"2 2 1.0 NaN NaN NaN \n",
"3 5,638 581.0 NaN NaN NaN \n",
"4 NaN NaN NaN NaN NaN "
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cust_data.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "948c98be-a60f-4251-9056-e6c829eae916",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"display:flex;flex-direction:row;justify-content:space-between;\">\n",
" <pre style=\"width: 100%; white-space: pre-wrap;\" id=\"6a9abd26-f473-45fa-8a6f-2451508cb1cb\">\n",
"# Drop the first column\n",
"cust_data = cust_data.drop(columns=cust_data.columns[0])\n",
"</pre>\n",
" <button style=\"height: fit-content;\" onclick=\"navigator.clipboard.writeText(JSON.parse(atob(`IlxuIyBEcm9wIHRoZSBmaXJzdCBjb2x1bW5cbmN1c3RfZGF0YSA9IGN1c3RfZGF0YS5kcm9wKGNvbHVtbnM9Y3VzdF9kYXRhLmNvbHVtbnNbMF0pXG4i`)))\">Copy</button>\n",
" </div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cust_data.sketch.howto(\"Drop the first column\")"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "38ed4e41-9b03-4077-923c-9dbc8ff26ba8",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Drop the first column\n",
"cust_data = cust_data.drop(columns=cust_data.columns[0])"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "8d57caba-5b80-4397-aa62-2f3f23c4c271",
"metadata": {
"tags": []
},
"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>Organization</th>\n",
" <th>2023-01</th>\n",
" <th>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Aquent</td>\n",
" <td>22</td>\n",
" <td>8.0</td>\n",
" <td>10.0</td>\n",
" <td>2.0</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",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>BioLife Solutions, Inc.</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ZyXel Communications Inc</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>BrightLine Eating Solutions LLC</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Casio America Inc</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Organization 2023-01 2023-02 2023-03 2023-04 \n",
"0 Aquent 22 8.0 10.0 2.0 \\\n",
"1 BioLife Solutions, Inc. NaN NaN NaN NaN \n",
"2 ZyXel Communications Inc NaN 1.0 1.0 NaN \n",
"3 BrightLine Eating Solutions LLC NaN NaN NaN NaN \n",
"4 Casio America Inc NaN NaN NaN NaN \n",
"\n",
" Churn Date 2022-01 2022-02 2022-03 2022-04 2022-05 2022-06 2022-07 2022-08 \n",
"0 2023-04 58 38 50 50 39 36 46 46 \\\n",
"1 2023-04 11 7 4 11 4 NaN NaN NaN \n",
"2 2023-04 1 1 2 1 2 4 2 2 \n",
"3 2023-03 10,362 7,890 7,272 8,177 8,468 7,524 8,509 5,638 \n",
"4 2023-03 NaN NaN NaN NaN NaN 1 NaN NaN \n",
"\n",
" 2022-09 2022-10 2022-11 2022-12 \n",
"0 43.0 27.0 24.0 26 \n",
"1 NaN NaN NaN NaN \n",
"2 1.0 NaN NaN NaN \n",
"3 581.0 NaN NaN NaN \n",
"4 NaN NaN NaN NaN "
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cust_data.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "a035f1e7-e9d9-48dd-b846-15b89646e0f9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"cust_data = cust_data.drop(columns=cust_data.columns[0])"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "f7a2b286-c6d4-4060-a427-4a210eacc42d",
"metadata": {
"tags": []
},
"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>2023-02</th>\n",
" <th>2023-03</th>\n",
" <th>2023-04</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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>8.0</td>\n",
" <td>10.0</td>\n",
" <td>2.0</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",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>NaN</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",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 2023-02 2023-03 2023-04 Churn Date 2022-01 2022-02 2022-03 2022-04 \n",
"0 8.0 10.0 2.0 2023-04 58 38 50 50 \\\n",
"1 NaN NaN NaN 2023-04 11 7 4 11 \n",
"2 1.0 1.0 NaN 2023-04 1 1 2 1 \n",
"3 NaN NaN NaN 2023-03 10,362 7,890 7,272 8,177 \n",
"\n",
" 2022-05 2022-06 2022-07 2022-08 2022-09 2022-10 2022-11 2022-12 \n",
"0 39 36 46 46 43.0 27.0 24.0 26 \n",
"1 4 NaN NaN NaN NaN NaN NaN NaN \n",
"2 2 4 2 2 1.0 NaN NaN NaN \n",
"3 8,468 7,524 8,509 5,638 581.0 NaN NaN NaN "
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cust_data.head(4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4637ba97-33cf-45d2-bf6f-1e54b4d0c421",
"metadata": {},
"outputs": [],
"source": []
}
],
"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 View Git Blame Copy Permalink