pgm1

 #pgm1

import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

from sklearn.datasets import fetch_california_housing



california_housing = fetch_california_housing()

print(california_housing.DESCR)



df = pd.DataFrame(california_housing.data, columns=california_housing.feature_names)

df['target'] = california_housing.target


print("First 5 rows of the dataset:")

print(df.head())



def plot_histograms(df):

    df.hist(bins=30, figsize=(12, 10))

    plt.suptitle("Histograms of Numerical Features", fontsize=16)

    plt.show()



def plot_boxplots(df):

    plt.figure(figsize=(15, 12))

    for i, feature in enumerate(df.columns):

        plt.subplot(3, 4, i + 1)

        sns.boxplot(x=df[feature])

        plt.title(f'Box Plot of {feature}')

    plt.tight_layout() 

    plt.show()




plot_histograms(df)

plot_boxplots(df)



print("Outliers Detection:")

outliers_summary = {}

numerical_features = df.select_dtypes(include=['float64', 'int64']).columns.tolist()


for feature in numerical_features:

    Q1 = df[feature].quantile(0.25)

    Q3 = df[feature].quantile(0.75)

    IQR = Q3 - Q1

    lower_bound = Q1 - 1.5 * IQR

    upper_bound = Q3 + 1.5 * IQR

    outliers = df[(df[feature] < lower_bound) | (df[feature] > upper_bound)]

    outliers_summary[feature] = len(outliers)

    print(f"{feature}: {len(outliers)} outliers")x


Comments

Post a Comment

Popular posts from this blog

pgm 2

  #pgm2 import pandas as pd import seaborn as sns import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing california_housing = fetch_california_housing() df = pd.DataFrame(california_housing.data, columns=california_housing.feature_names) df['target'] = california_housing.target correlation_matrix = df.corr() plt.figure(figsize=(12, 8)) sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', cbar=True) plt.title("Correlation Matrix Heatmap") plt.show() sns.pairplot(df, height=2.5, plot_kws={'alpha':0.7}) plt.suptitle("Pair Plot of California Housing Dataset", y=1.02) plt.show()
Read more

pgm5

 import numpy as np import matplotlib.pyplot as plt from collections import Counter # --- Data Setup --- np.random.seed(42) data = np.random.rand(100) train, test = data[:50], data[50:] train_labels = ["Class1" if x <= 0.5 else "Class2" for x in train] true_labels = ["Class1" if x <= 0.5 else "Class2" for x in test] # --- KNN Function --- def knn(x, train_data, labels, k):     distances = sorted(((abs(x - xi), yi) for xi, yi in zip(train_data, labels)))     nearest = distances[:k]     return Counter(yi for _, yi in nearest).most_common(1)[0][0] # --- Classification and Plotting --- k_values = [1, 3, 5, 20, 30] for k in k_values:     predictions = [knn(x, train, train_labels, k) for x in test]     accuracy = round(np.mean([pred == true for pred, true in zip(predictions, true_labels)]), 2)          print(f"\n--- k = {k} | Accuracy: {accuracy} ---")     for i, (x, p) in enumerate(zip(test, predi...
Read more

pgm 4

 #pgm4 import pandas as pd def find_s_algorithm(data):     print("Training data:")     print(data)     attributes = data.columns[:-1]     class_label = data.columns[-1]       hypothesis = None     for index, row in data.iterrows():         if row[class_label] == 'Yes':  # only consider positive examples             if hypothesis is None:                 hypothesis = list(row[attributes])             else:                 for i, value in enumerate(row[attributes]):                     if hypothesis[i] != value:                         hypothesis[i] = '?'  # generalize the hypothesis     if hypothesis is None:      ...
Read more