lab7

 import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.datasets import fetch_california_housing

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression

from sklearn.preprocessing import PolynomialFeatures, StandardScaler

from sklearn.pipeline import make_pipeline

from sklearn.metrics import mean_squared_error, r2_score


def plot_results(X_test, y_test, y_pred, xlabel, ylabel, title):

    plt.scatter(X_test, y_test, color="blue", label="Actual")

    plt.plot(X_test, y_pred, color="red", label="Predicted")

    plt.xlabel(xlabel)

    plt.ylabel(ylabel)

    plt.title(title)

    plt.legend()

    plt.show()

    print(f"{title}")

    print("Mean Squared Error:", mean_squared_error(y_test, y_pred))

    print("R^2 Score:", r2_score(y_test, y_pred))

def linear_regression():

    data = fetch_california_housing(as_frame=True)

    X, y = data.data[["AveRooms"]], data.target

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    model = LinearRegression().fit(X_train, y_train)

    plot_results(

        X_test, y_test, model.predict(X_test),

        "AveRooms", "Median Home Value ($100K)",

        "Linear Regression - California Housing"

    )

def polynomial_regression():

    url = "https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data"

    cols = ["mpg", "cyl", "disp", "hp", "wt", "acc", "yr", "origin"]

    data = pd.read_csv(url, sep=r'\s+', names=cols, na_values="?").dropna()

    X, y = data[["disp"]], data["mpg"]

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    model = make_pipeline(

        PolynomialFeatures(2),

        StandardScaler(),

        LinearRegression()

    ).fit(X_train, y_train)

    plot_results(

        X_test, y_test, model.predict(X_test),

        "Displacement", "MPG",

        "Polynomial Regression - Auto MPG"

    )

if __name__ == "__main__":

    linear_regression()

    polynomial_regression()


Comments

Post a Comment

Popular posts from this blog

lab9

 import numpy as np from sklearn.datasets import fetch_olivetti_faces from sklearn.model_selection import train_test_split, cross_val_score from sklearn.naive_bayes import GaussianNB from sklearn.metrics import accuracy_score, classification_report, confusion_matrix import matplotlib.pyplot as plt data = fetch_olivetti_faces(shuffle=True, random_state=42) X, y = data.data, data.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) gnb = GaussianNB() gnb.fit(X_train, y_train) y_pred = gnb.predict(X_test) print(f'Accuracy: {accuracy_score(y_test, y_pred) * 100:.2f}%') print("\nClassification Report:") print(classification_report(y_test, y_pred, zero_division=0)) print("\nConfusion Matrix:") print(confusion_matrix(y_test, y_pred)) missing_labels = set(np.unique(y_test)) - set(np.unique(y_pred)) if missing_labels:     print(f"\n⚠️ Labels not predicted at all: {missing_labels}") cv_accuracy = cross_val_score(gn...
Read more

lab2

import pandas as pd import seaborn as sns import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing california_data = fetch_california_housing(as_frame=True) data = california_data.frame correlation_matrix = data.corr() plt.figure(figsize=(10, 8)) sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5) plt.title('Correlation Matrix of California Housing Features') plt.show() sns.pairplot(data, diag_kind='kde', plot_kws={'alpha': 0.5}) plt.suptitle('Pair Plot of California Housing Features', y=1.02) plt.show() //Ye link copy and paste kr .Time :12.56 https://drive.google.com/file/d/1eLbcuKmeWo_GdHFEF3WnXFBcO2fVkZAe/view?usp=sharing
Read more

lab10

 import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import warnings from sklearn.datasets import load_breast_cancer from sklearn.cluster import KMeans from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from sklearn.metrics import confusion_matrix, classification_report warnings.filterwarnings("ignore", category=UserWarning) warnings.filterwarnings("ignore", category=FutureWarning) data = load_breast_cancer() X = data.data y = data.target scaler = StandardScaler() X_scaled = scaler.fit_transform(X) kmeans = KMeans(n_clusters=2, random_state=42, n_init=10) y_kmeans = kmeans.fit_predict(X_scaled) print("Confusion Matrix:") print(confusion_matrix(y, y_kmeans)) print("\nClassification Report:") print(classification_report(y, y_kmeans)) pca = PCA(n_components=2) X_pca = pca.fit_transform(X_scaled) df = pd.DataFrame(X_pca, columns=['PC1', 'PC2']) df['Cluste...
Read more