Set 1 – Titanic Dataset (Seaborn)

import seaborn as sns

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import StandardScaler, LabelEncoder

from sklearn.ensemble import RandomForestClassifier

from sklearn.svm import SVC

from sklearn.metrics import classification_report, ConfusionMatrixDisplay

import matplotlib.pyplot as plt

# Load dataset

df = sns.load_dataset('titanic')

# Preprocessing

df.drop(['deck', 'embark_town', 'alive'], axis=1, inplace=True)

df.dropna(inplace=True)

label_cols = df.select_dtypes(include=['object', 'category']).columns

df[label_cols] = df[label_cols].apply(LabelEncoder().fit_transform)

# Feature selection

X = df.drop('survived', axis=1)

y = df['survived']

X = StandardScaler().fit_transform(X)

# Train/test split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Random Forest

rf = RandomForestClassifier()

rf.fit(X_train, y_train)

y_pred_rf = rf.predict(X_test)
# SVM

svm = SVC()

svm.fit(X_train, y_train)

y_pred_svm = svm.predict(X_test)

# Evaluation

print("Random Forest:\n", classification_report(y_test, y_pred_rf))

print("SVM:\n", classification_report(y_test, y_pred_svm))

# Plot

fig, ax = plt.subplots(1, 2, figsize=(12, 5))

ConfusionMatrixDisplay.from_estimator(rf, X_test, y_test, ax=ax[0], cmap='Blues')

ax[0].title.set_text('Random Forest')

ConfusionMatrixDisplay.from_estimator(svm, X_test, y_test, ax=ax[1], cmap='Oranges')

ax[1].title.set_text('SVM')

plt.tight_layout()

plt.show()

Set 2 – Iris Dataset

from sklearn.datasets import load_iris

from sklearn.tree import DecisionTreeClassifier

from sklearn.decomposition import PCA

from sklearn.metrics import precision_score, f1_score

# Load and split

iris = load_iris()

X, y = iris.data, iris.target

# Step A – Decision Tree on full features

clf = DecisionTreeClassifier()
clf.fit(X, y)

y_pred = clf.predict(X)

print("Full Features:\nPrecision:", precision_score(y, y_pred, average='macro'), "F1:", f1_score(y,

# Step B – PCA reduced features

pca = PCA(n_components=2)

X_reduced = pca.fit_transform(X)

clf_pca = DecisionTreeClassifier()

clf_pca.fit(X_reduced, y)

y_pred_pca = clf_pca.predict(X_reduced)

print("Reduced Features:\nPrecision:", precision_score(y, y_pred_pca, average='macro'), "F1:",

# Visualization

plt.figure(figsize=(10, 4))

plt.subplot(1, 2, 1)

plt.scatter(X[:, 0], X[:, 1], c=y)

plt.title("Original Features")

plt.subplot(1, 2, 2)

plt.scatter(X_reduced[:, 0], X_reduced[:, 1], c=y)

plt.title("PCA Reduced Features")

plt.tight_layout()

plt.show()

Set 3 – Indian Pima Diabetes Dataset

import pandas as pd

from sklearn.ensemble import RandomForestClassifier

from sklearn.svm import SVC

from sklearn.preprocessing import StandardScaler

from sklearn.model_selection import train_test_split

from sklearn.metrics import classification_report

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-
diabetes.data.csv"

col_names = ['Preg', 'Glucose', 'BP', 'SkinThick', 'Insulin', 'BMI', 'DPF', 'Age', 'Outcome']

df = pd.read_csv(url, names=col_names)

# Preprocessing

X = df.drop('Outcome', axis=1)

y = df['Outcome']

X = StandardScaler().fit_transform(X)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Models

rf = RandomForestClassifier()

rf.fit(X_train, y_train)

print("Random Forest:\n", classification_report(y_test, rf.predict(X_test)))

svm = SVC()

svm.fit(X_train, y_train)

print("SVM:\n", classification_report(y_test, svm.predict(X_test)))

Set 4 – Stock Price Dataset (Linear Regression & Random Forest)

import pandas as pd

from sklearn.linear_model import LinearRegression

from sklearn.ensemble import RandomForestRegressor

from sklearn.model_selection import train_test_split

from sklearn.metrics import mean_squared_error, r2_score

import matplotlib.pyplot as plt

# Load a stock dataset (using Yahoo Finance via pandas_datareader or a CSV file)
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/a10.csv") # Replace
with actual stock data

df['date'] = pd.to_datetime(df['date'])

df['month'] = df['date'].dt.month

df['year'] = df['date'].dt.year

X = df[['month', 'year']]

y = df['value']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Linear Regression

lr = LinearRegression()

lr.fit(X_train, y_train)

y_pred_lr = lr.predict(X_test)

# Random Forest

rf = RandomForestRegressor()

rf.fit(X_train, y_train)

y_pred_rf = rf.predict(X_test)

# Evaluation

print("Linear Regression R2:", r2_score(y_test, y_pred_lr))

print("Random Forest R2:", r2_score(y_test, y_pred_rf))

# Plot

plt.plot(y_test.values, label='Actual')

plt.plot(y_pred_lr, label='Linear Regression')

plt.plot(y_pred_rf, label='Random Forest')

plt.legend()

plt.title("Stock Price Prediction")

Set 5 – MNIST Neural Network & KNN

import tensorflow as tf

from tensorflow.keras.layers import Dense, Flatten

from tensorflow.keras.models import Sequential

from tensorflow.keras.datasets import mnist

from sklearn.neighbors import KNeighborsClassifier

from sklearn.metrics import accuracy_score

# Load dataset

(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train_nn, x_test_nn = x_train / 255.0, x_test / 255.0

# Neural Network

model = Sequential([

Flatten(input_shape=(28, 28)),

Dense(128, activation='relu'),

Dense(256, activation='relu'),

Dense(512, activation='relu'),

Dense(1024, activation='relu'),

Dense(10, activation='softmax')

])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

history = model.fit(x_train_nn, y_train, epochs=100, validation_split=0.2, verbose=0)

# Accuracy

val_acc = history.history['val_accuracy'][-1]

print("Validation Accuracy after 100 epochs:", val_acc)

x_train_flat = x_train.reshape((x_train.shape[0], -1)) / 255.0

x_test_flat = x_test.reshape((x_test.shape[0], -1)) / 255.0

knn = KNeighborsClassifier()

knn.fit(x_train_flat, y_train)

y_pred_knn = knn.predict(x_test_flat)

print("KNN Accuracy:", accuracy_score(y_test, y_pred_knn))

Set 6 – Bayesian Belief Network & EM Algorithm

# Bayesian Belief Network using pgmpy

from pgmpy.models import BayesianModel

from pgmpy.estimators import MaximumLikelihoodEstimator

from pgmpy.inference import VariableElimination

import pandas as pd

data = pd.DataFrame([

['sunny', 'hot', 'high', 'FALSE', 'no'],

['sunny', 'hot', 'high', 'TRUE', 'no'],

['overcast', 'hot', 'high', 'FALSE', 'yes'],

['rainy', 'mild', 'high', 'FALSE', 'yes'],

], columns=['outlook', 'temperature', 'humidity', 'windy', 'play'])

model = BayesianModel([('outlook', 'play'), ('humidity', 'play'), ('windy', 'play')])

model.fit(data, estimator=MaximumLikelihoodEstimator)

infer = VariableElimination(model)

print(infer.map_query(['play'], evidence={'outlook': 'sunny'}))

# EM Clustering

from sklearn.mixture import GaussianMixture

from sklearn.datasets import make_blobs

import matplotlib.pyplot as plt

gmm = GaussianMixture(n_components=3)

gmm.fit(X)

labels = gmm.predict(X)

plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis')

plt.title("EM Clustering")

plt.show()

Set 7 – House Price Dataset (Multiple Algorithms)

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression

from sklearn.tree import DecisionTreeRegressor

from sklearn.svm import SVR

from sklearn.ensemble import RandomForestRegressor

from sklearn.metrics import r2_score

import matplotlib.pyplot as plt

df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv")

X = df.drop('medv', axis=1)

y = df['medv']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

models = {

"Linear": LinearRegression(),

"DecisionTree": DecisionTreeRegressor(),

"SVM": SVR(),

"RandomForest": RandomForestRegressor()
}

results = {}

for name, model in models.items():

model.fit(X_train, y_train)

pred = model.predict(X_test)

results[name] = r2_score(y_test, pred)

plt.bar(results.keys(), results.values())

plt.ylabel("R2 Score")

plt.title("Model Comparison - House Prices")

plt.show()

Set 8 – Flights Dataset from Seaborn

import seaborn as sns

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import LabelEncoder

import matplotlib.pyplot as plt

df = sns.load_dataset("flights")

df['month'] = LabelEncoder().fit_transform(df['month'])

X = df[['month', 'year']]

y = df['passengers']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

lr = LinearRegression()

lr.fit(X_train, y_train)

y_pred = lr.predict(X_test)

plt.scatter(y_test, y_pred)
plt.xlabel("Actual")

plt.ylabel("Predicted")

plt.title("Flights Prediction (Linear Regression)")

plt.show()

Viva Question Answers Summary

1. Machine Learning: Field of AI that enables systems to learn from data.

2. Supervised vs Unsupervised: Labeled data vs unlabeled data learning.

3. Classification vs Regression: Discrete labels vs continuous output.

4. Underfitting/Overfitting: Too simple vs too complex models.

5. Feature Selection/Extraction: Choosing vs transforming features.

6. Dimensionality Reduction: Reducing feature space (e.g., PCA).

7. Bias-Variance Tradeoff: Balance between model simplicity and complexity.

8. Entropy/Information Gain: Measures used in decision trees.

9. Bagging/Boosting: Ensemble methods to improve performance.

10. Support Vectors: Key data points used in SVM.

11. K-Means Disadvantages: Need for k, poor with noise, non-convex clusters.

12. Core/Border/Noise in DBSCAN: Density-based clustering points.

13. Lazy Learning: Delays learning until prediction (e.g., KNN).

14. Distance-Based ML: KNN, K-means.

15. Activation Functions: ReLU, Sigmoid, Tanh, Leaky ReLU, Softmax.

16. Naive Bayes Applications: Spam filtering, sentiment analysis, text classification.