Spaces:
Runtime error
Runtime error
File size: 2,203 Bytes
524248c 04f5cbf 524248c e9f7f55 524248c 04f5cbf 524248c 04f5cbf 524248c |
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 |
import pandas as pd
import numpy as np
import nltk
import re
from nltk.corpus import stopwords
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import PassiveAggressiveClassifier
import gradio as gr
from transformers import pipeline
# Download NLTK resources if not already downloaded
nltk.download('stopwords')
nltk.download('punkt')
nltk.download('wordnet')
nltk.download('omw-1.4')
# Load the dataset
df = pd.read_csv('disaster_tweets.csv') # Update path to your CSV file
# Data preprocessing
def clean_tweet(txt):
txt = txt.lower()
words = nltk.word_tokenize(txt)
stop = set(stopwords.words('english'))
words = [word for word in words if word not in stop]
words = ' '.join(words)
txt = re.sub('[^a-z]', ' ', words)
return txt
df['clean_text'] = df['text'].apply(clean_tweet)
# Split data into features and target
X = df['clean_text']
y = df['target']
# Splitting the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=0)
# TF-IDF Vectorization
tfidf_vectorizer = TfidfVectorizer(stop_words='english', max_df=0.8, ngram_range=(1, 3))
tfidf_train = tfidf_vectorizer.fit_transform(X_train)
tfidf_test = tfidf_vectorizer.transform(X_test)
# Model training
passive_aggressive = PassiveAggressiveClassifier()
passive_aggressive.fit(tfidf_train, y_train)
# Load the Hugging Face model
classifier = pipeline("text-classification", model="distilbert-base-uncased")
# Function for making predictions using the Hugging Face model
def predict_disaster_tweets(text):
cleaned_text = clean_tweet(text)
prediction = classifier(cleaned_text)[0]
label = prediction['label']
score = prediction['score']
return f"Label: {label}, Score: {score}"
# Gradio Interface setup
iface = gr.Interface(
fn=predict_disaster_tweets,
inputs=gr.Textbox(label="Enter Tweet Text", placeholder="Type here..."),
outputs=gr.Textbox(label="Prediction"),
title="Disaster Tweet Classifier",
description="Predict whether a tweet indicates a disaster or not."
)
iface.launch(share=True)
|