🔹 General Steps to Run Programs in Anaconda / Jupyter Notebook

1. Install Anaconda (from anaconda.com/download).
2. Open Anaconda Navigator.
3. Click Launch under Jupyter Notebook.
4. Your browser will open at http://localhost:8888/tree.
5. Click New → Python 3 (ipykernel) to create a new notebook.
6. Write or paste your Python code in a cell.
7. Press Shift + Enter to execute the cell.
8. Save your work: File → Save and Checkpoint.

🧩 Problem Set 1 – Control Structures & Data Import/Export

1. Use loops (for/while) and if-else statements for logic building.
2. Import data with import pandas as pd → pd.read_csv('filename.csv').
3. Clean and process data (drop missing values, rename columns, etc.).
4. Export using df.to_csv('output.csv').

🤖 Problem Set 2 – KNN Classification (e.g., Iris Dataset)

1. Import: from sklearn.neighbors import KNeighborsClassifier.
2. Load data: from sklearn.datasets import load_iris.
3. Split dataset using train_test_split.
4. Fit model: knn.fit(X_train, y_train).
5. Predict: y_pred = knn.predict(X_test).
6. Evaluate accuracy using accuracy_score().

🧠 Problem Set 3 – Naïve Bayes Classifier

1. Import: from sklearn.naive_bayes import GaussianNB.
2. Prepare features and labels (X, y).
3. Train the model: model.fit(X_train, y_train).
4. Predict using model.predict(X_test).
5. Evaluate using accuracy, precision, recall, and F1-score.

🛒 Problem Set 4 – Apriori Algorithm (Market Basket Analysis)

1. Install library: pip install mlxtend.
2. Import: from mlxtend.frequent_patterns import apriori, association_rules.
3. Load dataset (e.g., Online Retail Dataset).
4. Convert transactions into 0/1 format using one-hot encoding.
5. Apply apriori(df, min_support=0.05, use_colnames=True).
6. Generate rules using association_rules().

📊 Problem Set 5 – K-Means Clustering

1. Import: from sklearn.cluster import KMeans.
2. Load a dataset (e.g., Iris, Customer, or Fruit dataset).
3. Preprocess the data (scaling if needed).
4. Choose number of clusters (k) using the elbow method.
5. Apply clustering: kmeans = KMeans(n_clusters=k).
6. Visualize using matplotlib.pyplot scatter plots.

📈 Problem Set 6 – Model Comparison and Evaluation

1. Use datasets like Iris, Fruits, or Online Retail.
2. Compare models: Logistic Regression, SVM, and KNN using accuracy scores.
3. Visualize results with bar or line charts.

pip install pandas numpy matplotlib scikit-learn mlxtend

1. Load the Fruit dataset using pandas.
2. Preprocess and encode categorical features if needed.
3. Split data into training and testing sets.
4. Train models: Logistic Regression, SVM, and KNN on training data.
5. Evaluate each model on testing data using accuracy score.
6. Compare accuracy values in a table or bar chart.
7. Conclude which model performs best on Fruit dataset.

1. Load the Iris dataset from scikit-learn.
2. View first and last few rows using head() and tail().
3. Split data into training and testing sets (80/20).
4. Train KNN model and predict on test set.
5. Calculate accuracy and confusion matrix.
6. Discuss classification results (how well classes are separated).

1. Load Online Retail dataset using pandas.
2. Clean data (remove nulls, filter valid invoices).
3. Convert transactions into one-hot encoded format.
4. Apply Apriori algorithm with minimum support threshold.
5. Generate association rules (support, confidence, lift).
6. Analyze which products are frequently bought together.

1. Choose a dataset (e.g., Iris, Social Network Ads, or any CSV file).
2. Preprocess and split the dataset into training and testing parts.
3. Train Naive Bayes classifier on the training data.
4. Train KNN classifier on the same data.
5. Test both models and record predictions.
6. Compare accuracy and precision for both classifiers.
7. Discuss which model performs better and why.

1. Load the Iris dataset using pandas or scikit-learn.
2. Select numeric columns for clustering.
3. Use Elbow Method to find the optimal number of clusters.
4. Apply K-Means algorithm and assign cluster labels.
5. Visualize clusters using scatter plot (sepal or petal features).
6. Analyze how well the clusters match actual species.

1. Load a Customer Segmentation dataset (e.g., Mall Customers).
2. Use features like Age, Income, and Spending Score.
3. Decide number of clusters (k) using the Elbow Method.
4. Run K-Means and assign cluster labels to each customer.
5. Visualize clusters to interpret customer groups.
6. Use results for targeted marketing insights.

1. Load Fruit dataset containing measurements like weight, size, color score.
2. Normalize data to bring all features to same scale.
3. Apply K-Means clustering with chosen k value.
4. Visualize clusters and analyze fruit group patterns.
5. Interpret which features drive clustering results.