Solved all the questions with one logic change

assignment1/assignment1.py

@@ -0,0 +1,100 @@
+import numpy as np 
+import pandas as pd
+from sklearn.linear_model import LinearRegression
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error, r2_score 
+from sklearn.preprocessing import PolynomialFeatures
+from sklearn.pipeline import make_pipeline
+
+np.seterr(divide='ignore', invalid='ignore')
+
+name= ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
+dataset_file = "housing.csv"
+df=pd.read_csv(dataset_file, delim_whitespace=True, names=name)
+df.head()
+
+row,col=df.shape
+print("DF has ",row, "rows and ", col, " columns")
+df.info()
+
+df.corr()
+
+
+df.describe()
+x = df['LSTAT'].to_numpy().reshape(row, 1)
+y = df['MEDV'].to_numpy().reshape(row, 1)
+
+print(x.shape)
+print(y.shape)
+
+scaler = StandardScaler()
+scaler.fit(x)
+#y=scaler.fit(y)
+x=scaler.transform(x)
+
+x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2,random_state = 22)
+model = LinearRegression()
+model.fit(x_train, y_train)
+
+prediction=model.predict(x_test)
+Rsquared = r2_score(y_test, prediction)
+RMSE = np.sqrt(mean_squared_error(y_test, prediction))
+print("RMSE:",RMSE)
+print("R^2: ",Rsquared)
+print(x_train.shape)
+print(y_train.shape)
+import matplotlib.pyplot as plt
+plt.scatter(x_train,y_train)
+plt.plot(x_train,model.predict(x_train))
+
+
+polynomial = PolynomialFeatures(degree=2)
+model_2 = make_pipeline(polynomial,model)
+model_2.fit(x_train,y_train)
+prediction_2=model_2.predict(x_test)
+Rsquared = r2_score(y_test, prediction_2)
+RMSER = np.sqrt(mean_squared_error(y_test, prediction_2))
+print("RMSE:",RMSE)
+print("R^2: ",Rsquared)
+plt.figure()
+plt.scatter(x_train,y_train,s=15)
+plt.plot(x_train,model_2.predict(x_train),color="r")
+plt.title("Polynomial regression with degree "+str(2))
+plt.show()
+
+polynomial = PolynomialFeatures(degree=20)
+model_2 = make_pipeline(polynomial,model)
+model_2.fit(x_train,y_train)
+prediction_2=model_2.predict(x_test)
+Rsquared = r2_score(y_test, prediction_2)
+RMSE = np.sqrt(mean_squared_error(y_test, prediction_2))
+print("RMSE:",RMSE)
+print("R^2: ",Rsquared)
+plt.figure()
+plt.scatter(x_train,y_train,s=15)
+plt.plot(x_train,model_2.predict(x_train),color="r")
+plt.title("Polynomial regression with degree 20 "+str(2))
+plt.show()
+
+x2 = df[['LSTAT','RM',"PTRATIO"]].to_numpy()
+y2 = df[['MEDV']].to_numpy()
+
+
+scaler = StandardScaler()
+scaler.fit(x2)
+#y=scaler.fit(y)
+x2=scaler.transform(x2)
+
+x_train, x_test, y_train, y_test = train_test_split(x2,y,test_size=0.2,random_state = 22)
+model = LinearRegression()
+model.fit(x_train, y_train)
+
+prediction=model.predict(x_test)
+Rsquared  = r2_score(y_test, prediction)
+RMSE = np.sqrt(mean_squared_error(y_test, prediction))
+print("RMSE:",RMSE)
+print("R^2: ",Rsquared)
+print(x_train.shape)
+print(y_train.shape)
+

assignment1/assignment1_output.txt

@@ -0,0 +1,35 @@
+Table has 506rows and 14 columns
+<class 'pandas.core.frame.DataFrame'>
+RangeIndex: 506 entries, 0 to 505
+Data columns (total 14 columns):
+ #   Column   Non-Null Count  Dtype  
+---  ------   --------------  -----  
+ 0   CRIM     506 non-null    float64
+ 1   ZN       506 non-null    float64
+ 2   INDUS    506 non-null    float64
+ 3   CHAS     506 non-null    int64  
+ 4   NOX      506 non-null    float64
+ 5   RM       506 non-null    float64
+ 6   AGE      506 non-null    float64
+ 7   DIS      506 non-null    float64
+ 8   RAD      506 non-null    int64  
+ 9   TAX      506 non-null    float64
+ 10  PTRATIO  506 non-null    float64
+ 11  B        506 non-null    float64
+ 12  LSTAT    506 non-null    float64
+ 13  MEDV     506 non-null    float64
+dtypes: float64(12), int64(2)
+memory usage: 55.5 KB
+Linear Regression
+RMSE: 6.558372421381304
+R^2:  0.5149044976402835
+Polynomial Regression
+RMSE: 6.558372421381304
+R^2:  0.5857844942953512
+polynomial with 20 degree
+RMSE: 5.701888182388953
+R^2:  0.6333324378319982
+Multiple Features 'LSTAT','RM','PTRATIO'
+RMSE: 4.974434993788514
+adjusted R Squared 0.7123807719300754
+R^2:  0.720923917318291

assignment2/assignment2.ipynb

@@ -0,0 +1,224 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "255 Assignment 2.ipynb",
+      "private_outputs": true,
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "i8U-1XufkmSg"
+      },
+      "source": [
+        "from sklearn.datasets import fetch_lfw_people\n",
+        "from sklearn.svm import SVC\n",
+        "from sklearn.decomposition import PCA as RandomizedPCA\n",
+        "from sklearn.pipeline import make_pipeline\n",
+        "from sklearn.svm import SVC\n",
+        "import seaborn as sns\n",
+        "from sklearn.pipeline import make_pipeline\n",
+        "from sklearn import model_selection\n",
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "from sklearn import metrics"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "CD0jWoE9kxM0"
+      },
+      "source": [
+        "faces = fetch_lfw_people(min_faces_per_person=60)\n",
+        "print('data loaded')\n"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "XOkqgViXk6CF"
+      },
+      "source": [
+        "target_names = faces.target_names\n",
+        "n, h, w = faces.images.shape"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "i1VL_vrCm7yy"
+      },
+      "source": [
+        "photos = faces.data\n",
+        "labels = faces.target\n",
+        "xtrain, xtest, ytrain, ytest = model_selection.train_test_split(photos, labels, test_size=0.25,random_state=42)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "XadLyIGel0ZY"
+      },
+      "source": [
+        "pca = RandomizedPCA(n_components=150, svd_solver='randomized', whiten=True, random_state=42).fit(xtrain)\n",
+        "svc = SVC(kernel='rbf', class_weight='balanced')\n",
+        "model = make_pipeline(pca, svc)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "R_ns5nZnncyH"
+      },
+      "source": [
+        "C = np.logspace(-1, 5, 4)\n",
+        "gammas = np.logspace(-3, 0, 4)\n",
+        "params = dict(svc__gamma=gammas, svc__C=C)\n",
+        "gsv = model_selection.GridSearchCV(model, params)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "jVFZ328OoZZp"
+      },
+      "source": [
+        "gsv = gsv.fit(xtrain, ytrain)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "_Tzq1kwYplRv"
+      },
+      "source": [
+        "print(gsv.best_params_)\n",
+        "model = gsv.best_estimator_\n",
+        "ypred = model.predict(xtest)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "g7U8iDsWrawZ"
+      },
+      "source": [
+        "print(ypred)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "dYgFtFldr0LT"
+      },
+      "source": [
+        "r_ind = np.random.choice(xtest.shape[0], size=24, replace=False)\n",
+        "photos = xtest[r_ind]\n",
+        "labels_actual = ytest[r_ind]\n",
+        "labels_pred_sample = ypred[r_ind]\n",
+        "names_pred = target_names[labels_pred_sample]\n",
+        "names_actual = target_names[labels_actual]\n",
+        "print(metrics.classification_report(ytest, ypred, target_names=target_names))"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "rDslZ7t4sWgR"
+      },
+      "source": [
+        "#CONFUSIN MATRIX\n",
+        "confusion_matrix = metrics.confusion_matrix(names_pred,names_actual,labels=target_names)\n",
+        "print(confusion_matrix)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Ec1zuYf9skgF"
+      },
+      "source": [
+        "#HEAT MAP\n",
+        "sns.heatmap(confusion_matrix, annot=True)\n",
+        "plt.xlabel('Actual')\n",
+        "plt.ylabel('Predicted')\n",
+        "plt.show(block=True)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "orYgVPjpvfhn"
+      },
+      "source": [
+        "n_row=4\n",
+        "n_col=6\n",
+        "fig_title=\"Predictions\"\n",
+        "fig = plt.figure(figsize=(1.8 * n_col, 2.4 * n_row))\n",
+        "plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)\n",
+        "for i in range(n_row * n_col):\n",
+        "  ax = fig.add_subplot(n_row, n_col, i + 1)\n",
+        "  ax.imshow(photos[i].reshape((h, w)), cmap=plt.cm.gray)\n",
+        "  fc = 'black'\n",
+        "  if names_pred[i]!=names_actual[i] :\n",
+        "    fc = 'red'\n",
+        "    title = \"Predicted: \"+names_pred[i]+\"\\nActual: \"+names_actual[i]\n",
+        "    ax.set_title(names_pred[i], size=12,color=fc)\n",
+        "    plt.xticks(())\n",
+        "    plt.yticks(())\n",
+        "if fig_title: \n",
+        "      fig.suptitle(fig_title+'\\n', fontsize=20)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "3hEgMHkewU87"
+      },
+      "source": [
+        ""
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}