Spaces:
Runtime error
Runtime error
File size: 2,734 Bytes
d48676d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
import joblib
import gradio as gr
# Load the dataset
data_df = pd.read_csv('homework01_text_data_group13.csv')
# Separate features and labels
X = data_df['reviews']
y = data_df['class']
# Split the data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
# Create bag-of-words representations
vectorizer = CountVectorizer()
X_train_counts = vectorizer.fit_transform(X_train)
X_test_counts = vectorizer.transform(X_test)
# Train the KNN model
knn_model = KNeighborsClassifier(n_neighbors=2, metric='euclidean')
knn_model.fit(X_train_counts, y_train)
# Train the Logistic Regression model
logistic_model = LogisticRegression(penalty='l2', C=1, random_state=0)
logistic_model.fit(X_train_counts, y_train)
# Save the trained models
joblib.dump(knn_model, 'best_knn_model.pkl')
joblib.dump(logistic_model, 'best_logistic_regression_model.pkl')
def predict_knn(review_text, model=knn_model):
X_test = vectorizer.transform([review_text])
y_pred = model.predict(X_test)
y_pred_proba = model.predict_proba(X_test)[0]
return {'Positive': y_pred_proba[1], 'Negative': y_pred_proba[0]}
def predict_logistic(review_text, model=logistic_model):
X_test = vectorizer.transform([review_text])
y_pred = model.predict(X_test)
y_pred_proba = model.predict_proba(X_test)[0]
return {'Positive': y_pred_proba[1], 'Negative': y_pred_proba[0]}
models = ["KNN", "Logistic Regression"]
def predict(review_text, model):
if model == "KNN":
output = predict_knn(review_text)
else:
output = predict_logistic(review_text)
if output['Positive'] > output['Negative']:
sentiment = "Positive Feedback"
else:
sentiment = "Negative Feedback"
return sentiment, output
demo = gr.Interface(
fn=predict,
inputs=[
gr.Textbox(lines=2, placeholder="Enter your review comment...", label="Review Comment"),
gr.Dropdown(choices=models, label="Select Model")
],
outputs=[
gr.Textbox(label="Predicted Sentiment Class"),
gr.Label(num_top_classes=2, label="Predicted Probability")
],
examples=[
["This Food is interesting, I need a second Plate", "KNN"],
["This Food is interesting, I need a second Plate", "Logistic Regression"],
["The food was terrible, and the service was worse.", "KNN"],
["The food was terrible, and the service was worse.", "Logistic Regression"]
]
)
demo.launch() |