210700_1.pynb

Assignment 1/210700_Paridhi_1.ipynb

@@ -0,0 +1,215 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0aea084f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np \n",
+    "import pandas as pd\n",
+    "import matplotlib as mpl\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from math import sqrt\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9de1a867",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv('Dataset.csv',na_values=np.nan)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22c597ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1498d023",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.drop('CUST_ID',axis=1,inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11fa8a38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9a62c15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[\"CREDIT_LIMIT\"].fillna(df[\"CREDIT_LIMIT\"].mean(),inplace=True)\n",
+    "df[\"MINIMUM_PAYMENTS\"].fillna(df[\"MINIMUM_PAYMENTS\"].mean(),inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a6b42b0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5ea2ce88",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.skew(axis=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35fff664",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for col in df:\n",
+    "    df[col]=np.sqrt(df[col])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "de455143",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.skew(axis=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e03b082b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for col in df:\n",
+    "    plt.figure()\n",
+    "    sns.histplot(df[col])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "95409505",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "correlation = df.corr()\n",
+    "plt.figure(figsize=(17,17))\n",
+    "sns.heatmap(correlation, vmax=1, square=True,annot=True,cmap='cubehelix')\n",
+    "\n",
+    "plt.title('Correlation ')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0b0afd3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import StandardScaler\n",
+    "df_std = StandardScaler().fit_transform(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2855667",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.decomposition import PCA\n",
+    "pca = PCA().fit(df_std)\n",
+    "plt.plot(np.cumsum(pca.explained_variance_ratio_))\n",
+    "plt.xlim(0,15,1)\n",
+    "plt.xlabel('Number of components')\n",
+    "plt.ylabel('Cumulative explained variance')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "533ca1cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.decomposition import PCA \n",
+    "sklearn_pca = PCA(n_components=7)\n",
+    "Y_sklearn = sklearn_pca.fit_transform(df_std)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b754a92e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(Y_sklearn)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4b3e9fe",
+   "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": "3.10.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}