diff --git a/Customer Segmentation Analysis/Customer Segmentation.ipynb b/Customer Segmentation Analysis/Customer Segmentation.ipynb new file mode 100644 index 000000000..0c1742b6e --- /dev/null +++ b/Customer Segmentation Analysis/Customer Segmentation.ipynb @@ -0,0 +1,1040 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 57, + "id": "b20360c0", + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "id": "a510b2b5", + "metadata": {}, + "outputs": [], + "source": [ + "df= pd.read_csv(\"Shopping Mall Customer Segmentation Data .csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "id": "f7fe197d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + " | Customer ID | \n", + "Age | \n", + "Gender | \n", + "Annual Income | \n", + "Spending Score | \n", + "
---|---|---|---|---|---|
0 | \n", + "d410ea53-6661-42a9-ad3a-f554b05fd2a7 | \n", + "30 | \n", + "Male | \n", + "151479 | \n", + "89 | \n", + "
1 | \n", + "1770b26f-493f-46b6-837f-4237fb5a314e | \n", + "58 | \n", + "Female | \n", + "185088 | \n", + "95 | \n", + "
2 | \n", + "e81aa8eb-1767-4b77-87ce-1620dc732c5e | \n", + "62 | \n", + "Female | \n", + "70912 | \n", + "76 | \n", + "
3 | \n", + "9795712a-ad19-47bf-8886-4f997d6046e3 | \n", + "23 | \n", + "Male | \n", + "55460 | \n", + "57 | \n", + "
4 | \n", + "64139426-2226-4cd6-bf09-91bce4b4db5e | \n", + "24 | \n", + "Male | \n", + "153752 | \n", + "76 | \n", + "
... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
15074 | \n", + "a0504768-a85f-4930-ac24-55bc8e4fec9e | \n", + "29 | \n", + "Female | \n", + "97723 | \n", + "30 | \n", + "
15075 | \n", + "a08c4e0e-d1fe-48e7-9366-aab11ae409cd | \n", + "22 | \n", + "Male | \n", + "73361 | \n", + "74 | \n", + "
15076 | \n", + "0e87c25a-268c-401a-8ba1-7111dcde6f1a | \n", + "18 | \n", + "Female | \n", + "112337 | \n", + "48 | \n", + "
15077 | \n", + "5f388cbe-3373-4e16-b743-38f508f2249f | \n", + "26 | \n", + "Female | \n", + "94312 | \n", + "5 | \n", + "
15078 | \n", + "b8b8f561-ebca-4401-8afe-544c906554ba | \n", + "19 | \n", + "Male | \n", + "78045 | \n", + "2 | \n", + "
15079 rows × 5 columns
\n", + "\n", + " | Age | \n", + "Gender | \n", + "Annual Income | \n", + "Spending Score | \n", + "
---|---|---|---|---|
0 | \n", + "30 | \n", + "0 | \n", + "151479 | \n", + "89 | \n", + "
1 | \n", + "58 | \n", + "1 | \n", + "185088 | \n", + "95 | \n", + "
2 | \n", + "62 | \n", + "1 | \n", + "70912 | \n", + "76 | \n", + "
3 | \n", + "23 | \n", + "0 | \n", + "55460 | \n", + "57 | \n", + "
4 | \n", + "24 | \n", + "0 | \n", + "153752 | \n", + "76 | \n", + "
... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
15074 | \n", + "29 | \n", + "1 | \n", + "97723 | \n", + "30 | \n", + "
15075 | \n", + "22 | \n", + "0 | \n", + "73361 | \n", + "74 | \n", + "
15076 | \n", + "18 | \n", + "1 | \n", + "112337 | \n", + "48 | \n", + "
15077 | \n", + "26 | \n", + "1 | \n", + "94312 | \n", + "5 | \n", + "
15078 | \n", + "19 | \n", + "0 | \n", + "78045 | \n", + "2 | \n", + "
15079 rows × 4 columns
\n", + "\n", + " | Age | \n", + "Gender | \n", + "Annual Income | \n", + "Spending Score | \n", + "
---|---|---|---|---|
count | \n", + "15079.000000 | \n", + "15079.000000 | \n", + "15079.000000 | \n", + "15079.000000 | \n", + "
mean | \n", + "54.191591 | \n", + "0.496319 | \n", + "109742.880562 | \n", + "50.591617 | \n", + "
std | \n", + "21.119207 | \n", + "0.500003 | \n", + "52249.425866 | \n", + "28.726977 | \n", + "
min | \n", + "18.000000 | \n", + "0.000000 | \n", + "20022.000000 | \n", + "1.000000 | \n", + "
25% | \n", + "36.000000 | \n", + "0.000000 | \n", + "64141.000000 | \n", + "26.000000 | \n", + "
50% | \n", + "54.000000 | \n", + "0.000000 | \n", + "109190.000000 | \n", + "51.000000 | \n", + "
75% | \n", + "72.000000 | \n", + "1.000000 | \n", + "155008.000000 | \n", + "75.000000 | \n", + "
max | \n", + "90.000000 | \n", + "1.000000 | \n", + "199974.000000 | \n", + "100.000000 | \n", + "
LogisticRegression(max_iter=1000, multi_class='ovr')In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
LogisticRegression(max_iter=1000, multi_class='ovr')