🧩 Slip 1 – KNN Algorithm on Iris Dataset

1. Open Jupyter Notebook from Anaconda Navigator.
2. Create new file → Python 3.
3. Import required libraries: pandas, numpy, sklearn.
4. Load Iris dataset: from sklearn.datasets import load_iris.
5. Split data using train_test_split and apply KNeighborsClassifier.
6. Predict and check accuracy using accuracy_score().
7. Visualize clusters using matplotlib scatter plot.

---

🛒 Slip 2 – Apriori Algorithm (Online Retail Dataset)

1. Install mlxtend library using !pip install mlxtend.
2. Import: from mlxtend.frequent_patterns import apriori, association_rules.
3. Load and preprocess dataset into 0/1 transactional format.
4. Apply Apriori: apriori(df, min_support=0.05, use_colnames=True).
5. Generate rules: association_rules(frequent_itemsets, metric='lift', min_threshold=1).

---

🧠 Slip 3 – Naïve Bayes and KNN Classifier Comparison

1. Import libraries: from sklearn.naive_bayes import GaussianNB, KNeighborsClassifier.
2. Load dataset (e.g., Iris, Wine, or Diabetes).
3. Split into training and testing sets.
4. Train both models and predict results.
5. Compare accuracy and precision using classification_report().

---

📊 Slip 4 – K-Means Clustering

1. Import: from sklearn.cluster import KMeans.
2. Load dataset (e.g., Iris, Customers, Fruits).
3. Standardize features using StandardScaler.
4. Apply KMeans(n_clusters=3).
5. Visualize clusters with scatter plots.
6. Use elbow method to find optimal K.

---

🧮 Slip 5 – SVM for Classification

1. Import: from sklearn.svm import SVC.
2. Load dataset (e.g., Iris or Breast Cancer).
3. Train SVM with kernel types: linear and rbf.
4. Compare results on linearly vs non-linearly separable datasets.
5. Evaluate using confusion_matrix() and accuracy_score().

---

🧾 Slip 6 – Distinct Word Count (MapReduce)

1. Open Hadoop terminal in Cloudera / Ubuntu VM.
2. Upload file: hdfs dfs -put input.txt /user/input.
3. Run Word Count example:
   hadoop jar /usr/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples.jar wordcount /user/input /user/output
4. View results: hdfs dfs -cat /user/output/part-r-00000.
5. Each unique word and its count will be displayed.

---

📁 Slip 7 – Hadoop File Management (HDFS)

1. Start Hadoop: start-dfs.sh, start-yarn.sh.
2. Create directory: hdfs dfs -mkdir /user/data.
3. Add file: hdfs dfs -put sample.txt /user/data.
4. View file: hdfs dfs -cat /user/data/sample.txt.
5. Delete file: hdfs dfs -rm /user/data/sample.txt.

---

🧠 Slip 8 – Statistical Visualization (R Programming)

1. Open RStudio → create new R script.
2. Use built-in datasets like iris or mtcars.
3. Compute mean, median, mode, range, IQR, variance, SD.
4. Visualize using:
   • Histogram – hist()
   • Boxplot – boxplot()
   • Scatterplot – plot()

---

🌥️ Slip 9 – WordCloud using R

1. Install required packages: tm, wordcloud, RColorBrewer.
2. Load text data or input paragraph.
3. Create corpus and clean text (remove stopwords, punctuation).
4. Build term-document matrix using TermDocumentMatrix().
5. Generate cloud: wordcloud(words, freq, colors=brewer.pal(8,'Dark2')).

---

🧩 Slip 10 – Basic R Commands

1. Open RStudio console.
2. Use c(), seq(), mean(), median(), sd() for basic stats.
3. Perform matrix and dataframe operations.
4. Visualize with barplot(), plot(), hist().

---