noshot 0.3.1__py3-none-any.whl → 0.3.2__py3-none-any.whl

noshot/data/ML TS XAI/ML/1. PCA - EDA/PCA-EDA.ipynb

@@ -0,0 +1,207 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "8c414eda",
+   "metadata": {},
+   "source": [
+    "##### __Machine learnings Laboratory First Lab Basic EDA and Principle components analysis__"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1919dce4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.decomposition import PCA\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "459c19c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_table('input.txt', delimiter = ',', names = ['class name', 'left-weight', 'left-distance', 'right-weight', 'right-distance'])\n",
+    "#df = pd.read_csv('balance-scale.csv')\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4a1f3399",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"Shape\\t Size\")\n",
+    "print(df.shape, df.size)\n",
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ceb17e01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3950e04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e242d2e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.hist(df['class name'], color = 'green', label = 'Frequency Distribution')\n",
+    "plt.legend()\n",
+    "plt.title(\"Class Wise Count  ['L', 'B', 'R']\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "37654636",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, axs = plt.subplots(2,2)\n",
+    "axs[0][0].hist(df['left-weight'], color = 'orange', label = 'Left-Weight')\n",
+    "axs[0][1].hist(df['left-distance'], color = 'red', label = 'Lefft-distance')\n",
+    "axs[1][0].hist(df['right-weight'], color = 'green',label = 'right-weight')\n",
+    "axs[1][1].hist(df['right-distance'], color = 'indigo', label = 'right-distance')\n",
+    "fig.legend(loc = 'upper left')\n",
+    "fig.suptitle(\"Histogram For Features\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b033918",
+   "metadata": {},
+   "source": [
+    "##### __PCA__"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9d4bb7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "feature = ['left-weight','left-distance','right-weight','right-distance']\n",
+    "x = df.loc[:, feature]\n",
+    "y = df.loc[:, 'class name']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "de2b55cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = StandardScaler().fit_transform(x)\n",
+    "pca = PCA(n_components = 2)\n",
+    "pct = pca.fit_transform(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06bf0d31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "principal_df = pd.DataFrame(pct,columns=['pc1','pc2'])\n",
+    "print(\"principal-df:\\n\",principal_df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7dab85de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "finaldf= pd.concat([principal_df,df[['class name']]],axis=1)\n",
+    "print(\"finaldf:\\n\",finaldf)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "026ab3b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "finaldf.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53d0455b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = plt.figure(figsize = (8, 8))\n",
+    "ax = fig.add_subplot(1, 1, 1)\n",
+    "ax.set_xlabel('Principal Component 1', fontsize = 15)\n",
+    "ax.set_ylabel('Principal Component 2', fontsize = 15)\n",
+    "ax.set_title('2 component PCA', fontsize = 20)\n",
+    "targets = ['L','B','R']\n",
+    "colors = ['r', 'g','b']\n",
+    "for target, color in zip(targets, colors):\n",
+    "    indicesToKeep = finaldf['class name'] == target\n",
+    "    ax.scatter(finaldf.loc[indicesToKeep, 'pc1'], finaldf.loc[indicesToKeep, 'pc2'], c = color, s = 50)\n",
+    "ax.legend(targets)\n",
+    "ax.grid()"
+   ]
+  }
+ ],
+ "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}