QUESTION 1:
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score
import numpy as np
iris = load_iris()
x,y = iris.data, iris.target
logreg = LogisticRegression(max_iter=200,random_state=42)
k = 10
cv_scores = cross_val_score(logreg, x, y, cv=k, scoring='accuracy')
accuracy = np.mean(cv_scores)
print(f"Cross-validation scores:{cv_scores}")
print(f"accuracy:{accuracy: .4f}")
OUTPUT: Accuracy: 0.9733
QUESTION 2:
from sklearn.datasets import load_iris
from sklearn.model_selection import StratifiedKFold, cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
import numpy as np
# Load Iris dataset
iris = load_iris()
X, y = iris.data, iris.target
# Standardize the features for better performance
scaler = StandardScaler()
X = scaler.fit_transform(X)
# Define Logistic Regression model
model = LogisticRegression(max_iter=200)
# Set up Stratified K-Fold Cross-Validation
skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
# Perform cross-validation and calculate accuracy
scores = cross_val_score(model, X, y, cv=skf, scoring='accuracy')
# Display results
print(f"Accuracy: {scores.mean():.4f} ± {scores.std():.4f}")
OUTPUT: Accuracy: 0.9533 ± 0.0452
QUESTION 3:
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score, StratifiedKFold
import numpy as np
# Load the Iris dataset
iris = load_iris()
X = iris.data
y = iris.target
# Initialize the RandomForestClassifier
rf_model = RandomForestClassifier(random_state=42)
# Set up K-Fold Cross-Validation (Stratified to maintain class balance)
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
# Perform cross-validation and compute accuracy for each fold
cv_scores = cross_val_score(rf_model, X, y, cv=kfold, scoring='accuracy')
# Display the accuracy and standard deviation
print(f" Accuracy: {np.mean(cv_scores):.4f}")
OUTPUT: Accuracy: 0.9533
QUESTION 4:
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import StratifiedKFold, cross_val_score
import numpy as np
# Load the Iris dataset
iris = load_iris()
X = iris.data
y = iris.target
# Initialize the RandomForestClassifier
rf_model = RandomForestClassifier(random_state=42)
# Set up Stratified K-Fold Cross-Validation (10 folds)
stratified_kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
# Perform cross-validation and compute accuracy for each fold
cv_scores = cross_val_score(rf_model, X, y, cv=stratified_kfold, scoring='accuracy')
# Display the accuracy and standard deviation
print(f"Accuracy: {np.mean(cv_scores):.4f}")
OUTPUT: Accuracy: 0.9533
QUESTION 5:
# Load the Libras dataset
libras_data_path = '/mnt/data/movement_libras.data'
libras_data = pd.read_csv(libras_data_path, header=None)
# Display the first few rows of the dataset
libras_data.head()
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
# Separate features and target
X_libras = libras_data.iloc[:, :-1] # Features (columns 0 to 89)
y_libras = libras_data.iloc[:, -1] # Target (column 90)
# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_libras, y_libras, test_size=0.2, random_state=42)
# Train the random forest model
rf_model_libras = RandomForestClassifier(random_state=42)
rf_model_libras.fit(X_train, y_train)
# Make predictions on the test set
y_pred = rf_model_libras.predict(X_test)
# Calculate metrics
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')
accuracy, precision, recall, f1
OUTPUT:
Accuracy: 0.8055555555555556
Precision: 0.8413018308851642
Recall: 0.8055555555555556
F1-score: 0.8074919315718324
Classification Report:
precision recall f1-score support
1 0.88 0.88 0.88 8
2 0.83 0.62 0.71 8
3 1.00 0.83 0.91 6
4 1.00 0.91 0.95 11
5 0.75 0.75 0.75 8
6 1.00 0.50 0.67 6
7 0.88 1.00 0.93 7
8 0.40 0.67 0.50 3
9 0.77 1.00 0.87 10
10 1.00 0.78 0.88 9
11 0.60 1.00 0.75 3
12 0.71 0.83 0.77 6
13 0.67 0.67 0.67 6
14 0.64 0.88 0.74 8
15 1.00 0.67 0.80 9
accuracy 0.81 108
macro avg 0.81 0.80 0.78 108
weighted avg 0.84 0.81 0.81 108
