Practical for IML

 

Aim 1: Explore any one Machine Learning tool (Scikit-learn)

Program

# Exploring Scikit-learn library
import sklearn

print("Scikit-learn version:", sklearn.__version__)
print("Scikit-learn is used for machine learning tasks such as:")
print("Classification, Regression, Clustering, and Model Evaluation")

---

Aim 2: NumPy basic operations

Program

import numpy as np

# Convert list to 1D NumPy array
list1 = [1, 2, 3, 4, 5]
arr1 = np.array(list1)
print("1D Array:", arr1)

# Create 3x3 matrix from 2 to 10
matrix = np.arange(2, 11).reshape(3, 3)
print("3x3 Matrix:\n", matrix)

# Append values to array
arr2 = np.append(arr1, [6, 7])
print("Appended Array:", arr2)

# Reshape array from 3x2 to 2x3
arr3 = np.array([[1, 2], [3, 4], [5, 6]])
reshaped = arr3.reshape(2, 3)
print("Reshaped Array:\n", reshaped)

---

Aim 3: NumPy mathematical operations

Program

import numpy as np

a = np.array([10, 20, 30])
b = np.array([2, 4, 6])

# Element-wise operations
print("Addition:", a + b)
print("Subtraction:", a - b)
print("Multiplication:", a * b)
print("Division:", a / b)

# Round elements
c = np.array([1.2, 2.5, 3.7])
print("Rounded Array:", np.round(c))

# Mean across dimension
d = np.array([[1, 2, 3], [4, 5, 6]])
print("Mean across rows:", np.mean(d, axis=1))

# Difference between neighboring elements
e = np.array([10, 15, 25, 40])
print("Difference:", np.diff(e))

---

Aim 4: Pandas – missing values & duplicates

Program

import pandas as pd

data = {
    "Name": ["A", "B", "C", "C"],
    "Marks": [85, None, 90, 90]
}

df = pd.DataFrame(data)
print("Original DataFrame:\n", df)

# Drop missing values
df_no_nan = df.dropna()
print("\nAfter dropping missing values:\n", df_no_nan)

# Remove duplicates
df_no_dup = df_no_nan.drop_duplicates()
print("\nAfter removing duplicates:\n", df_no_dup)

---

Aim 5: Pandas – NaN checking and filtering

Program

import pandas as pd

data = {
    "A": [1, 2, None],
    "B": [4, 5, 6],
    "C": [None, 8, 9]
}

df = pd.DataFrame(data)
print("Original DataFrame:\n", df)

# Columns with all values present
print("\nColumns without NaN:\n", df.dropna(axis=1))

# Check NaN positions
print("\nNaN positions:\n", df.isna())

# Drop rows with any NaN
df_clean = df.dropna()
print("\nAfter dropping rows with NaN:\n", df_clean)

---

Aim 6: Scikit-learn dataset information

Program

from sklearn.datasets import load_iris

data = load_iris()

print("Keys:", data.keys())
print("Number of rows and columns:", data.data.shape)
print("Feature names:", data.feature_names)
print("Description:\n", data.DESCR[:500])

---

Aim 7: K-Nearest Neighbour algorithm

Program

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

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

# Split dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# KNN model
knn = KNeighborsClassifier(n_neighbors=3)
knn.fit(X_train, y_train)

# Prediction
y_pred = knn.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))

---

Aim 8: Machine Learning algorithm (Linear Regression)

Program

import numpy as np
from sklearn.linear_model import LinearRegression

# Dataset
X = np.array([[1], [2], [3], [4], [5]])
y = np.array([2, 4, 6, 8, 10])

# Model
model = LinearRegression()
model.fit(X, y)

# Prediction
prediction = model.predict([[6]])
print("Predicted value for input 6:", prediction)