Create app.py

app.py

@@ -0,0 +1,90 @@
+
+import gradio as gr
+import gradio.inputs
+
+import numpy as np
+import pandas as pd
+
+from sklearn.model_selection import train_test_split
+from simpletransformers.classification import ClassificationModel
+from sklearn.metrics import classification_report,confusion_matrix
+import re
+import nltk
+from nltk.corpus import stopwords
+nltk.download('stopwords')
+
+file_path = "https://raw.githubusercontent.com/alexvatti/full-stack-data-science/main/NLP-Exercises/Movie-Review/IMDB%20Dataset.csv"
+movies_df=pd.read_csv(file_path)
+
+def remove_tags(txt):
+    removelist = ""  # Add any characters you'd like to keep
+    # Remove HTML tags
+    result = re.sub(r'<[^>]+>', '', txt)
+    # Remove URLs
+    result = re.sub(r'https?://\S+', '', txt)
+    # Remove non-alphanumeric characters (except for those in the removelist)
+    result = re.sub(r'[^a-zA-Z0-9' + removelist + r'\s]', ' ', txt)
+    # Convert to lowercase
+    result = result.lower()
+    return result
+
+def remove_stop_wrods(txt):
+    stop_words = set(stopwords.words('english'))
+    return ' '.join([word for word in txt.split() if word not in (stop_words)])
+
+movies_df['review'] = movies_df['review'].apply(remove_tags)
+movies_df['review'] = movies_df['review'].apply(remove_stop_wrods)
+movies_df["Category"]=movies_df["sentiment"].apply(lambda x: 1 if x=='positive' else 0)
+
+X_train,X_test,y_train,y_test=train_test_split(movies_df['review'],movies_df["Category"],test_size=0.2,random_state=42)
+# Prepare the training and evaluation DataFrames for Simple Transformers
+train_df = pd.DataFrame({"text": X_train, "labels": y_train})
+eval_df = pd.DataFrame({"text": X_test, "labels": y_test})
+
+
+# Create a ClassificationModel
+model = ClassificationModel("bert", "bert-base-uncased", use_cuda=True)  # Set use_cuda=True if you have a GPU
+
+# Train the model
+model.train_model(train_df)
+
+# Evaluate the model
+result, model_outputs, wrong_predictions = model.eval_model(eval_df)
+model.save_model("sentiment_model")
+
+# Step 4: Load the Model for Prediction
+# To use the model later, reload it from the saved directory
+loaded_model = ClassificationModel("bert", "sentiment_model", use_cuda=True)
+
+# Step 5: Predict Sentiment for a New Review
+test_review = "This movie was absolutely fantastic! The acting was top-notch."
+review=remove_tags(test_review)
+review=remove_stop_wrods(review)
+predictions, raw_outputs = loaded_model.predict(review)
+print("Predictions:", predictions)  # Outputs the label (e.g., 1 for positive, 0 for negative)
+print("Raw Outputs:", raw_outputs)  # Outputs the raw model scores
+
+test_review ="I hated this movie. It was a complete waste of time."
+review=remove_tags(test_review)
+review=remove_stop_wrods(review)
+predictions, raw_outputs = loaded_model.predict(review)
+
+print("Predictions:", predictions)  # Outputs the label (e.g., 1 for positive, 0 for negative)
+print("Raw Outputs:", raw_outputs)  # Outputs the raw model scores
+
+def fn(test_review):
+    review=remove_tags(test_review)
+    review=remove_stop_wrods(review)
+    predictions, raw_outputs = loaded_model.predict(review)
+    return "Positive" if predictions==1 else "Negative"
+    
+description = "Give a review of a movie that you like(or hate, sarcasm intended XD) and the model will let you know just how much your review truely reflects your emotions. "
+here = gr.Interface(fn,
+                     inputs= gradio.inputs.Textbox( lines=1, placeholder=None, default="", label=None),
+                     outputs='text',
+                     title="Sentiment analysis of movie reviews",
+                     description=description,
+                     theme="peach",
+                     allow_flagging="auto",
+                     flagging_dir='flagging records')
+here.launch(inline=False)