📌 1️⃣ Measures of Central Tendency (Mean, Median, Mode)

python

CopyEdit

import numpy as np

import pandas as pd

from scipy import stats

# Sample Data

data = [10, 15, 12, 18, 15, 21, 25, 10, 30, 15]

# Mean

mean_value = np.mean(data)

print("Mean:", mean_value)

# Median

median_value = np.median(data)

print("Median:", median_value)

# Mode

mode_value = stats.mode(data, keepdims=True)

print("Mode:", mode_value.mode[0])

📌 2️⃣ Measures of Dispersion (Variance, Standard Deviation, Range, IQR)

python

CopyEdit

# Variance

variance_value = np.var(data, ddof=1) # Sample variance

print("Variance:", variance_value)

# Standard Deviation

std_dev = np.std(data, ddof=1)

print("Standard Deviation:", std_dev)

# Range

range_value = max(data) - min(data)

print("Range:", range_value)

# Interquartile Range (IQR)

q1 = np.percentile(data, 25)

q3 = np.percentile(data, 75)

iqr_value = q3 - q1

print("IQR:", iqr_value)

📌 3️⃣ Probability Distributions

Normal Distribution (Gaussian)

python

CopyEdit

import matplotlib.pyplot as plt

import scipy.stats as stats

# Generate data with normal distribution

mu, sigma = 0, 1 # Mean and Standard Deviation

normal_data = np.random.normal(mu, sigma, 1000)

# Plot normal distribution

plt.hist(normal_data, bins=30, density=True, alpha=0.6, color='g')

# Plot theoretical normal curve

xmin, xmax = plt.xlim()

x = np.linspace(xmin, xmax, 100)

p = stats.norm.pdf(x, mu, sigma)

plt.plot(x, p, 'k', linewidth=2)

plt.title("Normal Distribution")

plt.show()

Binomial Distribution

python

CopyEdit

# Binomial Distribution Example: 10 trials, 0.5 probability of success

n, p = 10, 0.5

binom_data = np.random.binomial(n, p, 1000)

# Plot histogram

plt.hist(binom_data, bins=10, density=True, alpha=0.6, color='b')

plt.title("Binomial Distribution")

plt.show()

📌 4️⃣ Hypothesis Testing

T-Test (Comparing Two Groups)

python

CopyEdit

# Generate two random samples

group1 = np.random.normal(50, 10, 30)

group2 = np.random.normal(55, 10, 30)

# Perform t-test

t_stat, p_value = stats.ttest_ind(group1, group2)

print("T-Test Statistic:", t_stat)

print("P-Value:", p_value)

Chi-Square Test (Categorical Variables)

python

CopyEdit
# Contingency Table

observed = np.array([[10, 20, 30], [6, 9, 17]])

# Perform Chi-Square Test

chi2, p, dof, expected = stats.chi2_contingency(observed)

print("Chi-Square Value:", chi2)

print("P-Value:", p)

📌 5️⃣ Correlation & Covariance

python

CopyEdit

# Generate two random datasets

x = np.random.rand(10)

y = np.random.rand(10)

# Correlation Coefficient

correlation = np.corrcoef(x, y)[0, 1]

print("Correlation Coefficient:", correlation)

# Covariance

covariance = np.cov(x, y)[0, 1]

print("Covariance:", covariance)

📌 6️⃣ Feature Selection Metrics

Mutual Information

python

CopyEdit

from sklearn.feature_selection import mutual_info_classif

# Example dataset

X = np.array([[1], [2], [3], [4], [5]])

y = np.array([0, 1, 0, 1, 0])

# Compute Mutual Information

mi_score = mutual_info_classif(X, y)

print("Mutual Information Score:", mi_score[0])

📌 7️⃣ Entropy & Information Gain (Decision Trees)

python

CopyEdit

from sklearn.tree import DecisionTreeClassifier

# Sample Data

X = np.array([[0], [1], [2], [3], [4], [5]])

y = np.array([0, 1, 0, 1, 0, 1])

# Train Decision Tree

clf = DecisionTreeClassifier(criterion='entropy')

clf.fit(X, y)

# Get Information Gain for each feature

feature_importance = clf.feature_importances_

print("Information Gain:", feature_importance)

🚀 Summary of Implemented Concepts

✅ Mean, Median, Mode

✅ Variance, Standard Deviation, Range, IQR
✅ Normal & Binomial Distributions
✅ T-Test & Chi-Square Test
✅ Correlation & Covariance
✅ Mutual Information & Information Gain

Machine learning algorithms are generally categorized into three main types:

1️⃣ Supervised Learning

In supervised learning, the algorithm is trained on labeled data, meaning each training example has
an input and a corresponding correct output.

🔹 Regression Algorithms (For predicting continuous values)

 Linear Regression

 Polynomial Regression

 Decision Tree Regression

 Random Forest Regression

 Support Vector Regression (SVR)

# Importing regression models

from sklearn.linear_model import LinearRegression

from sklearn.tree import DecisionTreeRegressor

from sklearn.ensemble import RandomForestRegressor

from sklearn.svm import SVR

# Initializing models with key parameters

linear_model = LinearRegression(fit_intercept=True, normalize='deprecated') #

fit_intercept=True means adding bias term

tree_model = DecisionTreeRegressor(criterion='mse', max_depth=5, min_samples_split=2)

forest_model = RandomForestRegressor(n_estimators=100, max_depth=10,

min_samples_split=2, random_state=42)

svr_model = SVR(kernel='rbf', C=1.0, epsilon=0.1) # C is the regularization parameter

🔹 Classification Algorithms (For predicting discrete categories)

 Logistic Regression

 K-Nearest Neighbors (KNN)

 Decision Tree

 Random Forest

 Support Vector Machine (SVM)

 Naïve Bayes

 Neural Networks

# Importing classification models

from sklearn.linear_model import LogisticRegression

from sklearn.neighbors import KNeighborsClassifier

 from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier

from sklearn.svm import SVC

from sklearn.naive_bayes import GaussianNB

# Initializing models with key parameters

logistic_model = LogisticRegression(penalty='l2', C=1.0, solver='lbfgs', max_iter=1000)

knn_model = KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2) # p=2 is for

Euclidean distance

tree_classifier = DecisionTreeClassifier(criterion='gini', max_depth=5, min_samples_split=2)

forest_classifier = RandomForestClassifier(n_estimators=100, max_depth=10,

min_samples_split=2, random_state=42)

svm_classifier = SVC(kernel='rbf', C=1.0, gamma='scale', probability=True)

naive_bayes = GaussianNB(var_smoothing=1e-9)

2️⃣ Unsupervised Learning

In unsupervised learning, the algorithm is trained on unlabeled data and tries to find hidden
patterns.

🔹 Clustering Algorithms (For grouping similar data points)

 K-Means

 Hierarchical Clustering

 DBSCAN (Density-Based Clustering)

# Importing clustering models

from sklearn.cluster import KMeans, DBSCAN

# Initializing models with key parameters

kmeans_model = KMeans(n_clusters=3, init='k-means++', max_iter=300, n_init=10,

random_state=42)

dbscan_model = DBSCAN(eps=0.5, min_samples=5, metric='euclidean')