Machine Learning is a branch of Artificial Intelligence where a computer learns patterns from data and uses those patterns to make predictions or decisions.

AI is the broad field of computer intelligence. ML is a part of AI that learns from data. Deep Learning is a part of ML that uses neural networks. Data Science uses data analysis, statistics, and ML to solve problems.

The main types are supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled data. Unsupervised learning finds hidden patterns. Reinforcement learning learns by reward and punishment.

Important tools are Python, NumPy, pandas, Matplotlib, Seaborn, scikit-learn, Jupyter Notebook, and VS Code.

Example Code

pip install numpy pandas matplotlib seaborn scikit-learn notebook

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import sklearn

print("ML setup successful")

A dataset is a collection of rows and columns. Rows are records. Columns are features. The target is the output we want to predict.

NumPy is used for numerical computing and arrays. It helps perform fast mathematical operations for ML.

Example Code

import numpy as np

marks = np.array([75, 80, 65, 90, 88])
print("Mean:", np.mean(marks))
print("Maximum:", np.max(marks))
print("Minimum:", np.min(marks))

pandas is used to read, clean, analyze, and prepare tabular data such as CSV and Excel files.

Example Code

import pandas as pd

df = pd.read_csv("students.csv")
print(df.head())
print(df.info())
print(df.describe())

Visualization helps understand trends, relationships, outliers, and distributions using charts.

Example Code

import matplotlib.pyplot as plt

hours = [1, 2, 3, 4, 5]
marks = [35, 45, 55, 65, 75]

plt.scatter(hours, marks)
plt.xlabel("Study Hours")
plt.ylabel("Marks")
plt.title("Study Hours vs Marks")
plt.show()

Preprocessing means cleaning and preparing data before training. It includes handling missing values, duplicates, encoding, and scaling.

Example Code

import pandas as pd

data = {"age":[20,None,22,25], "marks":[80,70,None,90]}
df = pd.DataFrame(data)

df["age"] = df["age"].fillna(df["age"].mean())
df["marks"] = df["marks"].fillna(df["marks"].mean())

print(df)

Train-test split separates data into training data and testing data to check performance on unseen examples.

Example Code

from sklearn.model_selection import train_test_split

X = df[["hours", "attendance"]]
y = df["marks"]

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

Linear Regression predicts continuous numeric values such as marks, salary, price, or temperature.

Example Code

import pandas as pd
from sklearn.linear_model import LinearRegression

data = {"hours":[1,2,3,4,5,6,7,8], "marks":[35,40,50,60,65,75,85,90]}
df = pd.DataFrame(data)

X = df[["hours"]]
y = df["marks"]

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

print(model.predict([[9]]))

Logistic Regression is used for classification problems such as pass/fail, spam/not spam, or disease/no disease.

Example Code

import pandas as pd
from sklearn.linear_model import LogisticRegression

data = {"hours":[1,2,3,4,5,6,7,8], "passed":[0,0,0,1,1,1,1,1]}
df = pd.DataFrame(data)

X = df[["hours"]]
y = df["passed"]

model = LogisticRegression()
model.fit(X, y)

print(model.predict([[6]]))

KNN predicts the class of a new point by checking nearest data points.

Example Code

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

iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data, iris.target, test_size=0.2, random_state=42
)

model = KNeighborsClassifier(n_neighbors=3)
model.fit(X_train, y_train)
pred = model.predict(X_test)

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

A Decision Tree works like a flowchart. Random Forest combines many trees for better performance.

Example Code

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data, iris.target, test_size=0.2, random_state=42
)

model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)
pred = model.predict(X_test)

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

SVM finds the best boundary between classes. It is useful for classification.

Example Code

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score

iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data, iris.target, test_size=0.2, random_state=42
)

model = SVC(kernel="linear")
model.fit(X_train, y_train)
pred = model.predict(X_test)

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

Naive Bayes is a probability-based classification algorithm often used in text classification and spam detection.

Example Code

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB

texts = ["win money now", "free prize", "hello friend", "meeting tomorrow"]
labels = [1, 1, 0, 0]

vectorizer = CountVectorizer()
X = vectorizer.fit_transform(texts)

model = MultinomialNB()
model.fit(X, labels)

new_text = ["win free prize"]
print(model.predict(vectorizer.transform(new_text)))

Clustering is unsupervised learning used to group similar data points. K-Means is a popular clustering algorithm.

Example Code

import pandas as pd
from sklearn.cluster import KMeans

data = {"income":[20000,25000,30000,80000,90000,95000],
        "spending":[30,35,40,75,80,85]}
df = pd.DataFrame(data)

model = KMeans(n_clusters=2, random_state=42, n_init=10)
df["cluster"] = model.fit_predict(df)

print(df)

Evaluation measures model performance. Regression uses MAE, MSE, RMSE, R2. Classification uses accuracy, precision, recall, F1, confusion matrix.

Example Code

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

print("Accuracy:", accuracy_score(y_test, predictions))
print(confusion_matrix(y_test, predictions))
print(classification_report(y_test, predictions))

Feature engineering means creating, selecting, or transforming features to improve model performance.

Example Code

df["total_marks"] = df["maths"] + df["science"] + df["english"]
df["average"] = df["total_marks"] / 3

df = pd.get_dummies(df, columns=["city"], drop_first=True)

Deep Learning uses neural networks with layers. It is powerful for images, audio, language, and complex patterns.

After training, a model can be saved using joblib and used inside apps such as Streamlit.

Example Code

import joblib

joblib.dump(model, "ml_model.pkl")

loaded_model = joblib.load("ml_model.pkl")
print(loaded_model.predict([[6]]))

Projects include student marks prediction, pass/fail classifier, spam detector, customer segmentation, and Iris classification.

Example Code

# Project ideas:
# 1. Student Marks Prediction
# 2. Pass or Fail Prediction
# 3. Spam Message Detection
# 4. Customer Segmentation
# 5. Iris Flower Classification

Final Practical Exam

1. Create a dataset.
2. Load it using pandas.
3. Clean missing values.
4. Visualize the data.
5. Split train and test data.
6. Train a model.
7. Evaluate the model.
8. Save the model.
9. Create a small app.