# Importing Libraries
import numpy as np
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

# ensures that the random numbers generated are the same every time the code runs.
np.random.seed(0)

#creates an array of 100 random numbers between 0 and 1.
X = np.random.rand(100, 1)         

#generates the target variable y using the linear relationship y = 2 + 3*X plus some random noise. This mimics real-world data that might not fit perfectly on a line.
y = 2 + 3 * X + np.random.rand(100, 1)       

# Create and fit the model
model = LinearRegression()
# fit means it calculates the best-fitting line through the data points.
model.fit(X, y)  

# Make predictions
X_test = np.array([[0], [1]])   #creates a test set with two points: 0 and 1
y_pred = model.predict(X_test)   # uses the fitted model to predict the y values for X_test


# Plot the results
plt.figure(figsize=(10, 6))
plt.scatter(X, y, color='b', label='Data points')
plt.plot(X_test, y_pred, color='r', label='Regression line')
plt.legend()
plt.xlabel('X')
plt.ylabel('y')
plt.title('Linear Regression Example\nimage by ishaangupta1201')
plt.show()


print(f"Intercept: {model.intercept_[0]:.2f}")
print(f"Coefficient: {model.coef_[0][0]:.2f}")

import numpy as np
from sklearn.linear_model import LogisticRegression

# Sample data: hours studied and pass/fail outcome
hours_studied = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10]).reshape(-1, 1)
outcome = np.array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1])

# Create and train the model
model = LogisticRegression()
model.fit(hours_studied, outcome)

# This results in an array of predicted binary outcomes (0 or 1).
predicted_outcome = model.predict(hours_studied)

# This results in an array where each sub-array contains two probabilities: the probability of failing and the probability of passing.
predicted_probabilities = model.predict_proba(hours_studied)

print("Predicted Outcomes:", predicted_outcome)
print("Predicted Probabilities:", predicted_probabilities)

from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report

# Load the iris dataset
iris = load_iris()
X, y = iris.data, iris.target

# splits the data into training and testing sets. 30% of the data is used for testing (test_size=0.3), and the rest for training. random_state=42 ensures the split is reproducible.
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# creates a decision tree classifier with a maximum depth of 3 levels and a fixed random state for reproducibility.
model = DecisionTreeClassifier(max_depth=3, random_state=42)
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)  #calculates the accuracy of the model’s predictions.
print(f"Accuracy: {accuracy:.2f}")
print("\nClassification Report:")
print(classification_report(y_test, y_pred, target_names=iris.target_names))

# Visualize the tree
plt.figure(figsize=(20,10))
plot_tree(model, feature_names=iris.feature_names, class_names=iris.target_names, filled=True, rounded=True)
plt.show()

from sklearn.datasets import load_wine
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split

# Load the wine dataset
X, y = load_wine(return_X_y=True)

# 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 and train the model
model = SVC(kernel='linear', random_state=42)
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

print("Predictions:", y_pred)

from sklearn.datasets import load_digits
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split

# Load the digits dataset
X, y = load_digits(return_X_y=True)

# 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 and train the model
model = GaussianNB()
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

print("Predictions:", y_pred)

from sklearn.datasets import load_iris
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split

# Load the iris dataset
X, y = load_iris(return_X_y=True)

# 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 and train the model
model = KNeighborsClassifier(n_neighbors=3)
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

print("Predictions:", y_pred)

from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans

# Create a synthetic dataset
X, _ = make_blobs(n_samples=100, centers=3, n_features=2, random_state=42)

# Create and train the model
model = KMeans(n_clusters=3, random_state=42)
model.fit(X)

# Predict the clusters
labels = model.predict(X)

print("Cluster labels:", labels)

from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

# Load the breast cancer dataset
X, y = load_breast_cancer(return_X_y=True)

# 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 and train the model
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

print("Predictions:", y_pred)

from sklearn.datasets import load_digits
from sklearn.decomposition import PCA

# Load the digits dataset
X, y = load_digits(return_X_y=True)

# Apply PCA to reduce the number of features
pca = PCA(n_compnotallow=2)
X_reduced = pca.fit_transform(X)

print("Reduced feature set shape:", X_reduced.shape)

import xgboost as xgb
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

# Load the breast cancer dataset
X, y = load_breast_cancer(return_X_y=True)

# 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 and train the model
model = xgb.XGBClassifier(random_state=42)
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

print("Predictions:", y_pred)