1. Find-S Algorithm

import pandas as pd
data = pd.read_csv("training-data.csv")
X = data.iloc[:, :-1].values
y = data.iloc[:, -1].values
hypothesis = ["0"] * len(X[0])
for i in range(len(X)):
 if str(y[i]).lower() == "yes":
 for j in range(len(hypothesis)):
 if hypothesis[j] == "0":
 hypothesis[j] = X[i][j]
 elif hypothesis[j] != X[i][j]:
 hypothesis[j] = "?"
print("Final Hypothesis:", hypothesis)
# training-data.csv
# Sky,Airtemp,Humidity,Enjoysport
# sunny,warm,normal,yes
# sunny,warm,high,yes
# rainy,cold,high,no




2. Candidate Elimination Algorithm

import numpy as np
import pandas as pd
data = pd.read_csv("training-data.csv")
X = np.array(data.iloc[:, :-1])
y = np.array(data.iloc[:, -1])
specific_h = X[0].copy()
general_h = [["?"] * len(specific_h) for _ in range(len(specific_h))]
for i, row in enumerate(X):
 if str(y[i]).lower() == "yes":
 for j in range(len(specific_h)):
 if row[j] != specific_h[j]:
 specific_h[j] = "?"
 general_h[j][j] = "?"
 else:
 for j in range(len(specific_h)):
 if row[j] != specific_h[j]:
 general_h[j][j] = specific_h[j]
 else:
 general_h[j][j] = "?"
general_h = [g for g in general_h if g != ["?"] * len(specific_h)]
print("Final Specific:", specific_h)
print("Final General:", general_h)






3. Decision Tree Classification – Breast Cancer Dataset

import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.metrics import accuracy_score
data = load_breast_cancer()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(
 X, y, test_size=0.2, random_state=42)
clf = DecisionTreeClassifier(random_state=42)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")
new_sample = [X_test[0]]
prediction = clf.predict(new_sample)
prediction_class = "Benign" if prediction[0] == 1 else "Malignant"
print(f"Predicted class for the new sample: {prediction_class}")
plt.figure(figsize=(18, 8))
plot_tree(clf, filled=True, feature_names=data.feature_names,
 class_names=data.target_names)
plt.title("Decision Tree - Breast Cancer Dataset")
plt.show()





4. Naive Bayes Classification – Student Result

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
df = pd.read_csv("book2.csv")
le = LabelEncoder()
for column in df.columns:
 df[column] = le.fit_transform(df[column])
X = df.iloc[:, :-1]
y = df.iloc[:, -1]
X_train, X_test, y_train, y_test = train_test_split(
 X, y, test_size=0.3, random_state=42)
model = GaussianNB()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy * 100)
new_sample = [[1, 1, 0]]
prediction = model.predict(new_sample)
result = "Pass" if prediction[0] == 1 else "Fail"
print("Prediction for new student:", result)






5. K-Nearest Neighbors (KNN) – Iris Dataset

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
data = load_iris()
x = data.data
y = data.target
x_train, x_test, y_train, y_test = train_test_split(
 x, y, test_size=0.2, random_state=42)
model = KNeighborsClassifier(n_neighbors=3)
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print("\nCorrect predictions:")
for i in range(len(y_test)):
 if y_test[i] == y_pred[i]:
 print(f"actual:{data.target_names[y_test[i]]},"
 f"predicted:{data.target_names[y_pred[i]]}")
print("\nWrong predictions:")
for i in range(len(y_test)):
 if y_test[i] != y_pred[i]:
 print(f"actual:{data.target_names[y_test[i]]},"
 f"predicted:{data.target_names[y_pred[i]]}")
correct = sum(y_test == y_pred)
accuracy = correct / len(y_test)
print("\nAccuracy:", accuracy * 100)





6. Artificial Neural Network (ANN) – Iris Dataset

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score
iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(
 X, y, test_size=0.2, random_state=42)
ann = MLPClassifier(hidden_layer_sizes=(5,),
 max_iter=1000, random_state=42)
ann.fit(X_train, y_train)
y_pred = ann.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Predicted values:", y_pred)
print("\nActual values:", y_test)
print(f"\nAccuracy: {accuracy * 100:.2f}%")





7. Linear Regression – Hours vs Marks

import matplotlib.pyplot as plt
import pandas as pd
from sklearn.linear_model import LinearRegression
data = pd.read_csv("p.csv")
X = data[['Hours']]
y = data['Marks']
model = LinearRegression()
model.fit(X, y)
y_pred = model.predict(X)
residuals = y - y_pred
plt.figure(figsize=(8, 5))
plt.scatter(X, y)
plt.plot(X, y_pred)
plt.title("Regression Analysis")
plt.xlabel("Hours")
plt.ylabel("Marks")
plt.show()
plt.figure(figsize=(8, 5))
plt.scatter(y_pred, residuals)
plt.axhline(y=0)
plt.title("Residual Plot")
plt.xlabel("Predicted Values")
plt.ylabel("Residuals")
plt.show()





8. Statistical Measures – Mean, Median, Mode, Variance and Standard Deviation

import numpy as np
from scipy import stats
data = [12, 15, 18, 15, 20, 22, 15, 18, 25, 30]
mean = np.mean(data)
median = np.median(data)
mode_res = stats.mode(data, keepdims=True)
variance = np.var(data)
std_dev = np.std(data)
print("Dataset:", data)
print("Mean =", mean)
print("Median =", median)
print("Mode =", mode_res.mode[0])
print("Variance =", variance)
print("Standard Deviation =", std_dev)




9. K-Means Clustering

import pandas as pd
from sklearn.cluster import KMeans
data = pd.read_csv("D:/p7.csv")
print("Dataset")
print(data)
X = data[['X', 'Y']]
kmeans = KMeans(n_clusters=2, random_state=0)
kmeans.fit(X)
data['Cluster'] = kmeans.labels_
print("\nClustered data")
print(data)
print("\nCentroids:")
print(kmeans.cluster_centers_)




10. Locally Weighted Linear Regression (LWLR)

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
df = pd.read_csv("D:/training2.csv")
x, y = df["x"].to_numpy(), df["y"].to_numpy()
X = np.c_[np.ones_like(x), x]
def lwlr(x0, tau=0.5):
 w = np.exp(-((x - x0) ** 2) / (2 * tau**2))
 theta = np.linalg.solve(
 X.T @ (w[:, None] * X),
 X.T @ (w * y))
 return np.array([1, x0]) @ theta
x_pred = np.linspace(x.min(), x.max(), 100)
y_pred = [lwlr(x0) for x0 in x_pred]
plt.scatter(x, y, c="red", label="Data Points")
plt.plot(x_pred, y_pred, "b-", label="LWR Curve")
plt.xlabel("X")
plt.ylabel("y")
plt.title("Locally Weighted Regression")
plt.legend()
plt.show()