Update app.py

app.py

@@ -21,8 +21,6 @@ from sklearn.naive_bayes import MultinomialNB
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
 from sklearn.feature_extraction.text import TfidfVectorizer
-from xgboost import XGBClassifier
-from lightgbm import LGBMClassifier
 from sklearn.svm import SVC
 # Ignore FutureWarning messages
 warnings.simplefilter(action='ignore', category=FutureWarning)
@@ -95,8 +93,6 @@ print('Data source import complete.')
 import numpy as np # linear algebra
 import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
 
-# Input data files are available in the read-only "../input/" directory
-# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
 
 import os
 for dirname, _, filenames in os.walk('/kaggle/input'):
@@ -158,136 +154,6 @@ vectorization = TfidfVectorizer()
 XV_train = vectorization.fit_transform(X_train)
 XV_test = vectorization.transform(X_test)
 
-"""## Random forest and boosting methods
-
-### Random forest
-"""
-
-rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)
-rf_classifier.fit(XV_train, y_train)
-
-rf_pred = rf_classifier.predict(XV_test)
-
-print("Random Forest Accuracy:", accuracy_score(y_test, rf_pred))
-
-print("\nRandom Forest Classification Report:")
-print(classification_report(y_test, rf_pred))
-
-ConfusionMatrixDisplay.from_predictions(y_test, rf_pred);
-
-"""### Adaboost boosting method"""
-
-ada_classifier = AdaBoostClassifier()
-ada_classifier.fit(XV_train, y_train)
-
-ada_pred = ada_classifier.predict(XV_test)
-
-print("AdaBoost Accuracy:", accuracy_score(y_test, ada_pred))
-
-print("\nAdaBoost Classification Report:")
-print(classification_report(y_test, ada_pred))
-
-ConfusionMatrixDisplay.from_predictions(y_test, ada_pred);
-
-"""### Gradient Boosting"""
-
-from sklearn.ensemble import GradientBoostingClassifier
-# Gradient Boosting Machine (GBM)
-gbm_classifier = GradientBoostingClassifier()
-gbm_classifier.fit(XV_train, y_train)
-y_pred_gbm = gbm_classifier.predict(XV_test)
-accuracy_gbm = accuracy_score(y_test, y_pred_gbm)
-print("\nGradient Boosting Machine (GBM) Model:")
-print("Accuracy:", accuracy_gbm)
-report_gbm = classification_report(y_test, y_pred_gbm)
-print("Gradient Boosting Machine (GBM) Classification Report:")
-print(report_gbm)
-# If you want to display confusion matrix for GBM, you can use:
-ConfusionMatrixDisplay.from_predictions(y_test, y_pred_gbm)
-
-"""### LightGBM"""
-
-import lightgbm as lgb
-from sklearn.metrics import accuracy_score, classification_report, ConfusionMatrixDisplay
-
-# LightGBM
-lgb_classifier = lgb.LGBMClassifier()
-lgb_classifier.fit(XV_train, y_train)
-y_pred_lgb = lgb_classifier.predict(XV_test)
-accuracy_lgb = accuracy_score(y_test, y_pred_lgb)
-print("\nLightGBM Model:")
-print("Accuracy:", accuracy_lgb)
-report_lgb = classification_report(y_test, y_pred_lgb)
-print("LightGBM Classification Report:")
-print(report_lgb)
-# If you want to display confusion matrix for LightGBM, you can use:
-ConfusionMatrixDisplay.from_predictions(y_test, y_pred_lgb)
-
-"""## SVM(Support Vector Machine)
-
-### Kernel ---> 'Linear'
-"""
-
-svm_classifier = SVC(kernel='linear')
-svm_classifier.fit(XV_train, y_train)
-
-svm_pred = svm_classifier.predict(XV_test)
-
-svm_accuracy = accuracy_score(y_test, svm_pred)
-print(f"SVM with linear kernel Accuracy:", svm_accuracy)
-
-print("\nSVM ( Kernel='linear' ) Classification Report:")
-print(classification_report(y_test, svm_pred))
-
-ConfusionMatrixDisplay.from_predictions(y_test,svm_pred);
-
-"""### Kernel--->'Poly'"""
-
-svm_classifier = SVC(kernel='poly')
-svm_classifier.fit(XV_train, y_train)
-
-svm_pred = svm_classifier.predict(XV_test)
-
-svm_accuracy = accuracy_score(y_test, svm_pred)
-print(f"SVM with poly kernel Accuracy:", svm_accuracy)
-
-print("\nSVM ( Kernel='Poly' ) Classification Report:")
-print(classification_report(y_test, svm_pred))
-
-ConfusionMatrixDisplay.from_predictions(y_test,svm_pred);
-
-"""### Kernel--->'RBF'"""
-
-svm_classifier = SVC(kernel='rbf')
-svm_classifier.fit(XV_train, y_train)
-
-svm_pred = svm_classifier.predict(XV_test)
-
-svm_accuracy = accuracy_score(y_test, svm_pred)
-print(f"SVM with rbf kernel Accuracy:", svm_accuracy)
-
-print("\nSVM ( Kernel='RBF' ) Classification Report:")
-print(classification_report(y_test, svm_pred))
-
-ConfusionMatrixDisplay.from_predictions(y_test,svm_pred);
-
-"""# Decision Tree"""
-
-from sklearn.tree import DecisionTreeClassifier, plot_tree
-decision_tree=DecisionTreeClassifier(max_depth=20)
-
-decision_tree.fit(XV_train,y_train)
-
-dt_pred=decision_tree.predict(XV_test)
-
-dt_accuracy=accuracy_score(y_test,dt_pred)
-print(f"Decision Tree Accuracy with depth=20:", dt_accuracy)
-
-print("\nDecision Tree Classification Report:")
-print(classification_report(y_test, dt_pred))
-
-ConfusionMatrixDisplay.from_predictions(y_test,dt_pred);
-
 """# Logistic Regression"""
 
 logistic_model = LogisticRegression(max_iter=100)
@@ -306,66 +172,6 @@ print(report_logistic)
 
 ConfusionMatrixDisplay.from_predictions(y_test,y_pred_logistic);
 
-"""# Naive Bayes"""
-
-nb_classifier = MultinomialNB()
-
-nb_classifier.fit(XV_train, y_train)
-
-y_pred = nb_classifier.predict(XV_test)
-
-accuracy = accuracy_score(y_test, y_pred)
-print("Naive Bayes Model:")
-print("Accuracy:", accuracy)
-
-report_naive_bayes = classification_report(y_test, y_pred)
-print("Naive Bayes Classification Report:")
-print(report_naive_bayes)
-
-ConfusionMatrixDisplay.from_predictions(y_test,dt_pred);
-
-"""# K Nearest Neightbors (KNN)"""
-
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.metrics import accuracy_score, classification_report, ConfusionMatrixDisplay
-
-# K-Nearest Neighbors (KNN)
-knn_classifier = KNeighborsClassifier()
-knn_classifier.fit(XV_train, y_train)
-y_pred_knn = knn_classifier.predict(XV_test)
-accuracy_knn = accuracy_score(y_test, y_pred_knn)
-print("K-Nearest Neighbors (KNN) Model:")
-print("Accuracy:", accuracy_knn)
-report_knn = classification_report(y_test, y_pred_knn)
-print("K-Nearest Neighbors (KNN) Classification Report:")
-print(report_knn)
-# If you want to display confusion matrix for KNN, you can use:
-ConfusionMatrixDisplay.from_predictions(y_test, y_pred_knn)
-
-"""# Test"""
-
-def output_lable(n):
-    if n == 0:
-        return "The Text Sentement is Negative"
-    elif n == 1:
-        return "The Text Sentement is Neutral"
-    elif n == 2:
-        return "The Text Sentement is Positive"
-
-def manual_testing(news):
-    testing_news = {"text":[news]}
-    new_def_test = pd.DataFrame(testing_news)
-    new_def_test["text"] = new_def_test["text"].apply(wp)
-    new_x_test = new_def_test["text"]
-    new_xv_test = vectorization.transform(new_x_test)
-    pred_lr = logistic_model.predict(new_xv_test)
-    pred_svm = svm_classifier.predict(new_xv_test)
-
-    return print((output_lable(pred_lr[0])))
-
-text = input("Enter Text to Classify ")
-manual_testing(text)
-
 pip install gradio
 
 import gradio as gr