1

 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
print(california_housing.DESCR)
print("First 5 rows of the dataset:")
print(df.head())
df.hist(bins=30, figsize=(12, 10))
plt.suptitle("Histograms of Numerical Features", fontsize=16)
plt.show()
plt.figure(figsize=(12, 10))
for i, feature in enumerate(df.columns[:-1]):  # Exclude 'target' column
    plt.subplot(3, 4, i + 1)  # 3 rows, 4 columns
    sns.boxplot(df[feature])
    plt.title(f'Box Plot of {feature}')
plt.tight_layout()
plt.show()
print("Outliers Detection:")
for feature in df.select_dtypes(include=['float64', 'int64']).columns:
    Q1, Q3 = df[feature].quantile([0.25, 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)]
    print(f"{feature}: {len(outliers)} outliers")

Comments

Post a Comment

Popular posts from this blog

9

import scipy.io, numpy as np, matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.naive_bayes import GaussianNB from sklearn.metrics import accuracy_score d = scipy.io.loadmat('olivettifaces.mat') X, y = d['faces'].T, np.repeat(np.arange(40), 10) Xt, Xs, yt, ys = train_test_split(X, y, test_size=0.3, stratify=y, random_state=42) m = GaussianNB().fit(Xt, yt) yp = m.predict(Xs) print("Acc: %.2f%%" % (accuracy_score(ys, yp) * 100)) i = np.random.choice(len(Xs), 20, replace=False) imgs = Xs[i].reshape(-1, 64, 64).transpose(0, 2, 1) plt.figure(figsize=(12,6)) for j in range(20):     plt.subplot(4, 5, j+1)     plt.imshow(imgs[j], cmap='gray')     plt.title(f"T:{ys[i[j]]}, P:{yp[i[j]]}", fontsize=8)     plt.axis('off') plt.tight_layout(); plt.show() #we need to upload olivettiface dataset
Read more

7

 import numpy as np, pandas as pd, seaborn as sns, matplotlib.pyplot as plt from sklearn.linear_model import LinearRegression from sklearn.model_selection import train_test_split from sklearn.preprocessing import PolynomialFeatures from sklearn.metrics import mean_squared_error, r2_score from sklearn.datasets import fetch_openml boston = fetch_openml(name='boston', version=1, as_frame=True) X, y = boston.data.values, boston.target.values Xt, Xs, yt, ys = train_test_split(X, y, test_size=0.2) m = LinearRegression().fit(Xt, yt) yp = m.predict(Xs) print("Linear R²=%.2f" % r2_score(ys, yp)) plt.scatter(Xs[:,5], ys, c='b'); plt.scatter(Xs[:,5], yp, c='r'); plt.title("Boston"); plt.show() df = sns.load_dataset('mpg').dropna() df['horsepower'] = pd.to_numeric(df['horsepower'], errors='coerce') df = df.dropna() X, y = df[['horsepower', 'weight']], df['mpg'] Xt, Xs, yt, ys = train_test_split(X, y...
Read more

10

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 import matplotlib.pyplot as plt X, y = load_breast_cancer(return_X_y=True) X = StandardScaler().fit_transform(X) y_pred = KMeans(n_clusters=2, random_state=42, n_init=10).fit_predict(X) print(confusion_matrix(y, y_pred)) print(classification_report(y, y_pred)) X_pca = PCA(2).fit_transform(X) plt.scatter(*X_pca.T, c=y_pred, cmap='coolwarm', alpha=0.7) plt.title("K-Means Clustering (PCA)") plt.show()
Read more