lab1

 import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn.datasets import fetch_california_housing

housing_data = fetch_california_housing()

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

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

print(df.head(5))

print("\nDataset Summary:")

print(df.describe())

df.hist(figsize=(12, 8), bins=30, edgecolor='black')

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

plt.show()

plt.figure(figsize=(12, 6))

df.boxplot(rot=45)

plt.title("Box Plots for All Numerical Features", fontsize=16)

plt.show()

Q1 = df.quantile(0.25)

Q3 = df.quantile(0.75)

IQR = Q3 - Q1

lower_bound = Q1 - 1.5 * IQR

upper_bound = Q3 + 1.5 * IQR

outliers = ((df < lower_bound) | (df > upper_bound)).sum()

print("\nNumber of Outliers in Each Feature:")

print(outliers)

plt.figure(figsize=(12, 8))

for i, col in enumerate(df.columns, 1):

    plt.subplot(3, 3, i)

    sns.boxplot(x=df[col], color="skyblue")

    plt.title(col)

plt.tight_layout()

plt.show()


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