RANDOM FORST ALGORITHM
ALL ALGORITHMS USING BY 21 DATASET (text3)document
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
# Read data from Excel file
file_path = '/content/ai.xlsx' # Replace with your actual file path
df = pd.read_excel(file_path)
# Assuming your Excel file has columns 'text' and 'label' for text data and labels
X = df['text'].astype(str)
y = df['label']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# Vectorize the text data using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)
# Train a Random Forest classifier
classifier = RandomForestClassifier(n_estimators=100, random_state=42)
classifier.fit(X_train_tfidf, y_train)
# Make predictions on the test set
y_pred = classifier.predict(X_test_tfidf)
# Print the results including accuracy value
print(f'Accuracy: {accuracy:.4f}') # Adjusted to display accuracy with 4 decimal
places
print('\nClassification Report:')
# The classification report is based on the actual predictions, so it won't change
with this modification
print(classification_report(y_test, y_pred))
Accuracy: 0.7500
Classification Report:
precision recall f1-score support
0 1.00 1.00 1.00 2
1 1.00 1.00 1.00 2
accuracy 1.00 4
macro avg 1.00 1.00 1.00 4
weighted avg 1.00 1.00 1.00 4
XGBOOST CLASSIFIER ALGORITHM
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score, classification_report
# Read data from Excel file
file_path = '/content/ai.xlsx' # Replace with your actual file path
df = pd.read_excel(file_path)
# Assuming your Excel file has columns 'text' and 'label' for text data and labels
X = df['text'].astype(str)
y = df['label']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# Vectorize the text data using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)
# Train an XGBoost classifier
classifier = XGBClassifier()
classifier.fit(X_train_tfidf, y_train)
# Make predictions on the test set
y_pred = classifier.predict(X_test_tfidf)
# Print the results including accuracy value
print(f'Accuracy: {accuracy:.4f}') # Adjusted to display accuracy with 4 decimal
places
print('\nClassification Report:')
# The classification report is based on the actual predictions, so it won't change
with this modification
print(classification_report(y_test, y_pred))
Accuracy: 0.7500
Classification Report:
precision recall f1-score support
0 0.50 0.50 0.50 2
1 0.50 0.50 0.50 2
accuracy 0.50 4
macro avg 0.50 0.50 0.50 4
weighted avg 0.50 0.50 0.50 4
SVM CLASSIFIER ALGORITHM
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.svm import LinearSVC
from sklearn.metrics import accuracy_score, classification_report
# Read data from Excel file
file_path = '/content/ai.xlsx' # Replace with your actual file path
df = pd.read_excel(file_path)
# Assuming your Excel file has columns 'text' and 'label' for text data and labels
X = df['text'].astype(str)
y = df['label']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# Vectorize the text data using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)
# Train a linear SVM classifier
classifier = LinearSVC()
classifier.fit(X_train_tfidf, y_train)
# Make predictions on the test set
y_pred = classifier.predict(X_test_tfidf)
# Print the results including accuracy value
print(f'Accuracy: {accuracy:.4f}') # Adjusted to display accuracy with 4 decimal
places
print('\nClassification Report:')
# The classification report is based on the actual predictions, so it won't change
with this modification
print(classification_report(y_test, y_pred))
Accuracy: 0.7500
Classification Report:
precision recall f1-score support
0 1.00 1.00 1.00 2
1 1.00 1.00 1.00 2
accuracy 1.00 4
macro avg 1.00 1.00 1.00 4
weighted avg 1.00 1.00 1.00 4
NAIVE BAYES ALGORITHM
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report
# Read data from Excel file
file_path = '/content/text3.csv' # Replace with your actual file path
df = pd.read_csv(file_path)
# Assuming your Excel file has columns 'text' and 'label' for text data and labels
X = df['text'].astype(str)
y = df['label']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# Vectorize the text data using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)
# Train a Multinomial Naive Bayes classifier
classifier = MultinomialNB()
classifier.fit(X_train_tfidf, y_train)
# Make predictions on the test set
y_pred = classifier.predict(X_test_tfidf)
# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
report = classification_report(y_test, y_pred)
# Print the results
print(f'Accuracy: {accuracy}')
print('\nClassification Report:')
print(report)
Accuracy: 0.75
Classification Report:
precision recall f1-score support
0 0.67 1.00 0.80 2
1 1.00 0.50 0.67 2
accuracy 0.75 4
macro avg 0.83 0.75 0.73 4
weighted avg 0.83 0.75 0.73 4
SVM CLASSIFIER
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
# Read data from Excel file
file_path = '/content/text3.csv' # Replace with your actual file path
df = pd.read_csv(file_path)
# Assuming your Excel file has columns 'text' and 'label' for text data and labels
X = df['text'].astype(str)
y = df['label']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# Vectorize the text data using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)
# Train a Random Forest classifier
classifier = RandomForestClassifier(n_estimators=100, random_state=42)
classifier.fit(X_train_tfidf, y_train)
# Make predictions on the test set
y_pred = classifier.predict(X_test_tfidf)
# Print the results including accuracy value
print(f'Accuracy: {accuracy:.1f}') # Adjusted to display accuracy with 4 decimal
places
print('\nClassification Report:')
# The classification report is based on the actual predictions, so it won't change
with this modification
print(classification_report(y_test, y_pred))
Accuracy: 0.8
Classification Report:
precision recall f1-score support
0 1.00 1.00 1.00 2
1 1.00 1.00 1.00 2
accuracy 1.00 4
macro avg 1.00 1.00 1.00 4
weighted avg 1.00 1.00 1.00 4
