ML4

import pandas as pd
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import ConfusionMatrixDisplay, accuracy_score, precision_score
from sklearn.metrics import classification_report
import matplotlib.pyplot as plt
df=pd.read_csv(r'C:\Users\user\Desktop\26_ML\emails.csv')
print(df.shape)

print(df.head())

#input data
x = df.drop(['Email No.','Prediction'], axis =1)
print(x.shape)

y = df['Prediction']
print(y.shape)

#checking balance of spam and not spam
print(y.value_counts())

#Feature Scaling
scaler = MinMaxScaler()
x_scaled = scaler.fit_transform(x)
print(x_scaled)


#Cross validation
x_train, x_test, y_train, y_test = train_test_split(x_scaled,y,random_state = 0, test_size = 0.25)
print(x_scaled.shape)
print(x_train.shape)
print(x_test.shape)

#create the object
knn = KNeighborsClassifier(n_neighbors=5)

#Train the algorithm
knn.fit(x_train,y_train)

#predict on test data
y_pred = knn.predict(x_test)
cm_display = ConfusionMatrixDisplay.from_predictions(y_test,y_pred)
print(y_test.value_counts())

#print accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")

#print precision
precision = precision_score(y_test, y_pred)
print(f"Precision: {precision * 100:.2f}%")

#print accuracy and precision
a = classification_report(y_test, y_pred)
print("report is : ", a)
plt.show()

/////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////


import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, precision_score

# Load the dataset
df = pd.read_csv('emails.csv')  # Adjust the path if needed

# Print column names to identify the correct target column
print("Columns in the dataset:", df.columns)

# Use the correct column name for labels
target_column = 'Prediction'  # Update this to the actual column name in your dataset

# Check if the target column exists
if target_column not in df.columns:
    raise ValueError(f"Target column '{target_column}' not found in the DataFrame. Available columns are: {df.columns}")

# Convert labels to binary values
df[target_column] = df[target_column].map({'spam': 1, 'ham': 0})

# Drop rows with missing target values
df = df.dropna(subset=[target_column])

# Separate features and target variable
X = df.drop(target_column, axis=1)
y = df[target_column]

# Check for and handle missing values in features
if X.isnull().sum().sum() > 0:
    print("Missing values found in features. Filling with mean values.")
    X = X.fillna(X.mean())

# Print shape of X and y before converting categorical variables
print(f"Shape of X before conversion: {X.shape}")

# Convert categorical features to numeric
X = pd.get_dummies(X)

# Print shape of X after converting categorical variables
print(f"Shape of X after conversion: {X.shape}")

# Split the data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Check the shapes of the train and test sets
print(f"Shape of X_train: {X_train.shape}")
print(f"Shape of X_test: {X_test.shape}")
print(f"Shape of y_train: {y_train.shape}")
print(f"Shape of y_test: {y_test.shape}")

# Scale features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Initialize and train the KNN classifier
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train_scaled, y_train)

# Make predictions
y_pred = knn.predict(X_test_scaled)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)

# Print the results
print(f"Accuracy: {accuracy:.2f}")
print(f"Precision: {precision:.2f}")

////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////

Problem Statement-Apply K-Nearest Neighbor Classifier on
Data set. Test for Accuracy and Precision.
Classify the email using the binary
classification method. Email Spam detection has two states: a) Normal State –
Not Spam, b) Abnormal State – Spam. Use K-Nearest Neighbors for classification.

Code:
import pandas as pd
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import ConfusionMatrixDisplay, accuracy_score, precision_score
from sklearn.metrics import classification_report
import matplotlib.pyplot as plt
df=pd.read_csv(r'C:\Users\user\Desktop\26_ML\emails.csv')
print(df.shape)

print(df.head())

#input data
x = df.drop(['Email No.','Prediction'], axis =1)
print(x.shape)

y = df['Prediction']
print(y.shape)

#checking balance of spam and not spam
print(y.value_counts())

#Feature Scaling
scaler = MinMaxScaler()
x_scaled = scaler.fit_transform(x)
print(x_scaled)


#Cross validation
x_train, x_test, y_train, y_test = train_test_split(x_scaled,y,random_state = 0, test_size = 0.25)
print(x_scaled.shape)
print(x_train.shape)
print(x_test.shape)

#create the object
knn = KNeighborsClassifier(n_neighbors=5)

#Train the algorithm
knn.fit(x_train,y_train)

#predict on test data
y_pred = knn.predict(x_test)
cm_display = ConfusionMatrixDisplay.from_predictions(y_test,y_pred)
print(y_test.value_counts())

#print accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")

#print precision
precision = precision_score(y_test, y_pred)
print(f"Precision: {precision * 100:.2f}%")

#print accuracy and precision
a = classification_report(y_test, y_pred)
print("report is : ", a)
plt.show()


/////////////////////////////////////////////////////////////////////////////////

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, precision_score

# Load the dataset
df = pd.read_csv('emails.csv')  # Adjust the path if needed
print("Initial DataFrame:")
print(df.head())  # Print the first few rows

# Print the unique values in the target column
target_column = 'Prediction'  # Update this to the actual column name in your dataset
print("Unique values in target column before mapping:", df[target_column].unique())

# Check for missing values in the target column
print("Missing values in target column:", df[target_column].isnull().sum())

# Commented out the mapping since values are already 0 and 1
# df[target_column] = df[target_column].map({'spam': 1, 'ham': 0})

# Drop rows with missing target values - Not needed here as we confirmed no missing values
# df = df.dropna(subset=[target_column])

# Check if the DataFrame is empty after dropping missing values
if df.shape[0] == 0:
    raise ValueError("No samples left after preprocessing. Check your dataset and processing steps.")

# Separate features and target variable
X = df.drop(target_column, axis=1)
y = df[target_column]

# Check for and handle missing values in features
if X.isnull().sum().sum() > 0:
    print("Missing values found in features. Filling with mean values.")
    X = X.fillna(X.mean())

# Print shape of X and y before converting categorical variables
print(f"Shape of X before conversion: {X.shape}")

# Convert categorical features to numeric
X = pd.get_dummies(X)

# Print shape of X after converting categorical variables
print(f"Shape of X after conversion: {X.shape}")

# Split the data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Check the shapes of the train and test sets
print(f"Shape of X_train: {X_train.shape}")
print(f"Shape of X_test: {X_test.shape}")
print(f"Shape of y_train: {y_train.shape}")
print(f"Shape of y_test: {y_test.shape}")

# Scale features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Initialize and train the KNN classifier
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train_scaled, y_train)

# Make predictions
y_pred = knn.predict(X_test_scaled)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)

# Print the results
print(f"Accuracy: {accuracy:.2f}")
print(f"Precision: {precision:.2f}")