Scribd Logo
Upload

Welcome to Scribd!

  • 4 views

    Data analytics

    Uploaded by

    LIBIN R K

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Data analytics

    Uploaded by

    LIBIN R K
    4 views10 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    4 views10 pages

    Data analytics

    Uploaded by

    LIBIN R K

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 10

    Exp1 (Linear regression)

    import numpy as np

    import pandas as pd

    import matplotlib.pyplot as plt

    from sklearn.model_selection import train_test_split

    from sklearn.linear_model import LinearRegression

    # Load dataset from CSV

    # Ensure your CSV has columns 'X' and 'Y'

    data = pd.read_csv('C:/Users/HP/Desktop/data1.csv')

    X = data['X'].values.reshape(-1, 1) # Features (Independent Variable)

    Y = data['Y'].values # Labels (Dependent Variable)

    # Split the data into training and testing sets

    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)

    # Create Linear Regression model and train it

    regressor = LinearRegression()

    regressor.fit(X_train, Y_train)

    # Predicting the Test set results

    Y_pred = regressor.predict(X_test)

    # Visualize the results

    plt.scatter(X_train, Y_train, color='blue', label='Training data') # Training data

    plt.scatter(X_test, Y_test, color='green', label='Test data (Actual)') # Test data (actual)

    plt.scatter(X_test, Y_pred, color='red', label='Test data (Predicted)') # Predicted test data

    plt.plot(X_train, regressor.predict(X_train), color='red', label='Regression Line') # Regression line

    plt.title('Linear Regression')

    plt.xlabel('X (Input)')

    plt.ylabel('Y (Output)')

    plt.legend()

    plt.show()
    # Output predicted values

    print("Predicted values for X_test:", Y_pred)

    Output

    Predicted values for X_test: [1.92857143]


    Exp 5 (K Means Clustering)

    import numpy as np

    import pandas as pd

    import matplotlib.pyplot as plt

    from sklearn.cluster import KMeans

    # Load dataset from CSV

    df = pd.read_csv('C:/Users/HP/Desktop/data2.csv')

    # Convert to numpy array

    X = df[['Feature1', 'Feature2']].values

    # Number of clusters

    k=3

    # Create and fit KMeans model

    kmeans = KMeans(n_clusters=k, random_state=42)

    kmeans.fit(X)

    # Predict cluster labels

    y_kmeans = kmeans.predict(X)

    # Plot the data points with cluster labels

    plt.scatter(X[:, 0], X[:, 1], c=y_kmeans, cmap='viridis', marker='o', label='Data Points')

    # Plot centroids

    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], c='red', marker='X', s=200,


    label='Centroids')

    plt.title('K-Means Clustering')

    plt.xlabel('Feature 1')
    plt.ylabel('Feature 2')

    plt.legend()

    plt.show()

    Output
    Exp 3 (Logistic Regression)

    import numpy as np

    import pandas as pd

    import matplotlib.pyplot as plt

    from sklearn.model_selection import train_test_split

    from sklearn.linear_model import LogisticRegression

    from sklearn.metrics import accuracy_score

    # Load dataset from CSV

    data = pd.read_csv('C:/Users/HP/Desktop/data3.csv')

    # Extract features and target

    X = data[['Feature']].values # Feature (independent variable)

    Y = data['Target'].values # Target (dependent variable, 0 or 1)

    # Split the data into training and testing sets

    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)

    # Create Logistic Regression model and train it

    classifier = LogisticRegression()

    classifier.fit(X_train, Y_train)

    # Predicting the Test set results

    Y_pred = classifier.predict(X_test)

    # Calculate Accuracy

    accuracy = accuracy_score(Y_test, Y_pred)

    # Visualize the results

    plt.scatter(X_train, Y_train, color='blue', label='Training data') # Training data

    plt.scatter(X_test, Y_test, color='green', label='Test data (Actual)') # Test data (actual)


    plt.scatter(X_test, Y_pred, color='red', label='Test data (Predicted)') # Predicted test data

    # Logistic Regression decision boundary

    X_range = np.linspace(min(X), max(X), 100).reshape(-1, 1) # Fine-grained X values for smoother


    curve

    Y_prob = classifier.predict_proba(X_range)[:, 1] # Probabilities for the positive class

    plt.plot(X_range, Y_prob, color='red', label='Logistic Regression Curve')

    plt.title('Logistic Regression')

    plt.xlabel('X (Input)')

    plt.ylabel('Probability/Output')

    plt.legend()

    plt.show()

    # Output predicted values and accuracy

    print("Predicted values for X_test:", Y_pred)

    print("Accuracy:", accuracy)

    Output

    Predicted values for X_test: [1]

    Accuracy: 0.0
    Exp 2 (Multiple Linear Regression)

    import pandas as pd

    import numpy as np

    import matplotlib.pyplot as plt

    from sklearn.model_selection import train_test_split

    from sklearn.linear_model import LinearRegression

    # Load dataset from CSV

    df = pd.read_csv('C:/Users/HP/Desktop/data4.csv')

    # Extract features (X) and target (Y)

    X = df[['Feature1', 'Feature2']].values # Features (independent variables)

    Y = df['Target'].values # Target (dependent variable)

    # Split the data into training and testing sets

    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)

    # Create Multiple Linear Regression model and train it

    regressor = LinearRegression()

    regressor.fit(X_train, Y_train)

    # Predicting the Test set results

    Y_pred = regressor.predict(X_test)

    # Visualize the results

    plt.scatter(Y_test, Y_pred, color='blue', label='Predicted vs Actual') # Predicted vs Actual

    plt.plot([min(Y_test), max(Y_test)], [min(Y_test), max(Y_test)], color='red', label='Best fit line') #


    Regression line

    plt.title('Multiple Linear Regression')

    plt.xlabel('Actual values')

    plt.ylabel('Predicted values')
    plt.legend()

    plt.show()

    Output

    Predicted values for X_test: [3.]


    Exp 4 (Apriori Algorithm)

    import pandas as pd

    from mlxtend.frequent_patterns import apriori, association_rules

    data = {'Transaction': ['T1', 'T2', 'T3', 'T4', 'T5'],

    'Items': [['Bread', 'Milk'], ['Bread', 'Diaper', 'Beer', 'Eggs'],

    ['Milk', 'Diaper', 'Beer', 'Cola'], ['Bread', 'Milk', 'Diaper', 'Beer'],

    ['Bread', 'Milk', 'Cola']]}

    df = pd.DataFrame(data)

    from mlxtend.preprocessing import TransactionEncoder

    te = TransactionEncoder()

    te_ary = te.fit(df['Items']).transform(df['Items'])

    df_encoded = pd.DataFrame(te_ary, columns=te.columns_)

    frequent_itemsets = apriori(df_encoded, min_support=0.4, use_colnames=True)

    rules = association_rules(frequent_itemsets, metric="confidence", min_threshold=0.5)

    print("Frequent Itemsets:")

    print(frequent_itemsets)

    print("\nAssociation Rules:")

    print(rules)
    Output

    You might also like