Pgr-7

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.impute import SimpleImputer
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")


df_boston = pd.read_csv("Boston housing dataset.csv")

print("Columns in dataset:", df_boston.columns.tolist())

X = df_boston.drop("MEDV", axis=1)
y = df_boston["MEDV"]

imputer = SimpleImputer(strategy='mean')
X = pd.DataFrame(imputer.fit_transform(X), columns=X.columns)

rm_index = df_boston.columns.get_loc("RM") - 1 

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
lr_model = LinearRegression()
lr_model.fit(X_train, y_train)
y_pred = lr_model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y_test, y_pred)

print("\nLinear Regression (Boston Housing CSV):")
print(f'Mean Squared Error: {mse:.2f}')
print(f'Root Mean Squared Error: {rmse:.2f}')
print(f'R-squared: {r2:.2f}')
plt.scatter(X_test.iloc[:, rm_index], y_test, color='blue', label='Actual')
plt.plot(X_test.iloc[:, rm_index], y_pred, color='red', label='Predicted', alpha=0.6)
plt.title("Linear Regression: Boston Housing (RM vs MEDV)")
plt.xlabel("Average Number of Rooms (RM)")
plt.ylabel("Median House Value (MEDV)")
plt.legend()
plt.show()

df_auto = sns.load_dataset('mpg').dropna()

X_poly = df_auto[['horsepower', 'weight']]
y_poly = df_auto['mpg']

X_train_poly, X_test_poly, y_train_poly, y_test_poly = train_test_split(X_poly, y_poly, test_size=0.2,
random_state=42)


poly = PolynomialFeatures(degree=3)
X_train_poly_transformed = poly.fit_transform(X_train_poly)
X_test_poly_transformed = poly.transform(X_test_poly)

poly_model = LinearRegression()
poly_model.fit(X_train_poly_transformed, y_train_poly)

y_pred_poly = poly_model.predict(X_test_poly_transformed)
mse_poly = mean_squared_error(y_test_poly, y_pred_poly)
rmse_poly = np.sqrt(mse_poly)
r2_poly = r2_score(y_test_poly, y_pred_poly)

print("\nPolynomial Regression (Auto MPG):")
print(f'Mean Squared Error: {mse_poly:.2f}')
print(f'Root Mean Squared Error: {rmse_poly:.2f}')
print(f'R-squared: {r2_poly:.2f}')


plt.scatter(X_test_poly['horsepower'], y_test_poly, color='blue', label='Actual')
plt.scatter(X_test_poly['horsepower'], y_pred_poly, color='red', label='Predicted', alpha=0.6)
plt.title("Polynomial Regression: Auto MPG (Horsepower vs MPG)")
plt.xlabel("Horsepower")
plt.ylabel("Miles per Gallon (MPG)")
plt.legend()
plt.show()

Comments

Post a Comment

Popular posts from this blog

Pgr-1

import pandas as pd 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()) # Display the first 5 rows 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=(12, 10))  for i, feature in enumerate(df.columns):   plt.subplot(3, 4, i+1) # Adjust the number of rows and columns accordingly   sns.boxplot(df[feature])   plt.title(f'Box Plot of {feature}')  plt.tight_layout()  plt.show() import matplotlib.pyplot as plt plot_histograms(df) plot_boxplots(df) print("Outliers Detection:") outliers_summary = {} numerical_features = df.select_dtypes(include=['float64', ...
Read more

Pgr-4

 import pandas as pd def find_s_algorithm(file_path):  data = pd.read_csv(file_path)  print("Training data:")  print(data)  attributes = data.columns[:-1]   class_label = data.columns[-1]   for index, row in data.iterrows():  if row[class_label] == 'Yes':   hypothesis = list(row[attributes])    break  for index, row in data.iterrows():  if row[class_label] == 'Yes':   for i, value in enumerate(row[attributes]):    if hypothesis[i] != value:      hypothesis[i] = '?' # Generalize hypothesis return hypothesis file_path = 'training_data.csv' # Provide the file path hypothesis = find_s_algorithm(file_path) print("\nThe final hypothesis is:", hypothesis)
Read more

Pgr-5

import numpy as np import matplotlib.pyplot as plt from collections import Counter data = np.random.rand(100) labels = ["Class1" if x <= 0.5 else "Class2" for x in data[:50]] def euclidean_distance(x1, x2):  return abs(x1 - x2) def knn_classifier(train_data, train_labels, test_point, k):  distances = [(euclidean_distance(test_point, train_data[i]), train_labels[i]) for i in   range(len(train_data))]  distances.sort(key=lambda x: x[0])  k_nearest_neighbors = distances[:k]  k_nearest_labels = [label for _, label in k_nearest_neighbors]  return Counter(k_nearest_labels).most_common(1)[0][0]  train_data = data[:50]  train_labels = labels  test_data = data[50:]  k_values = [1, 2, 3, 4, 5, 20, 30]  print("--- k-Nearest Neighbors Classification ---")  print("Training dataset: First 50 points labeled based on the rule (x <= 0.5 -> Class1, x > 0.5 ->  Class2)")  print("Testing dataset: Remaining 50 poi...
Read more