addedApp

17297781Karthik · Oct 21, 2024 · b360d54 · b360d54
1 parent c01e757
commit b360d54
Show file tree

Hide file tree

Showing 9 changed files with 75 additions and 8 deletions.
diff --git a/.github/workflows/docker-image.yml b/.github/workflows/docker-image.yml
@@ -0,0 +1 @@
+name: Docker Image CIon:  push:    branches: [ "main" ]  pull_request:    branches: [ "main" ]jobs:  build:    runs-on: ubuntu-latest    steps:    - uses: actions/checkout@v4    - name: Build the Docker image      run: docker build . --file Dockerfile --tag my-image-name:$(date +%s)

diff --git a/.idea/workspace.xml b/.idea/workspace.xml
diff --git a/Dockerfile b/Dockerfile
@@ -0,0 +1 @@
+# Use an official Python runtime as a base imageFROM python:3.11-slim# Set the working directory in the containerWORKDIR /app# Copy the requirements file into the containerCOPY requirements.txt .# Install dependenciesRUN pip install -r requirements.txt# Copy the current directory contents into the containerCOPY . .# Expose the port the app runs onEXPOSE 8080# Run the appCMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8080"]

diff --git a/app.py b/app.py
@@ -0,0 +1 @@
+import joblibimport refrom fastapi import FastAPI, Request, Formfrom fastapi.responses import HTMLResponsefrom fastapi.staticfiles import StaticFilesfrom fastapi.templating import Jinja2Templatesfrom nltk.corpus import stopwordsfrom nltk.stem.porter import PorterStemmerfrom pydantic import BaseModel# Load the model and vectorizer from the .pkl filesmodel = joblib.load(r'models/logistic_regression_model.pkl')vectorizer = joblib.load(r'models/tfidf_vectorizer.pkl')# Initialize FastAPI appapp = FastAPI()# Initialize the stemmerport_stem = PorterStemmer()# Mount the static directory for CSS filesapp.mount("static", StaticFiles(directory="static"), name="static")# Initialize templates directory for rendering HTMLtemplates = Jinja2Templates(directory="templates")def preprocess_text(text):    """Preprocess the input text by stemming and removing stopwords."""    stemmed_content = re.sub('[^a-zA-Z]', ' ', text)    stemmed_content = stemmed_content.lower()    stemmed_content = stemmed_content.split()    stemmed_content = [port_stem.stem(word) for word in stemmed_content if not word in stopwords.words('english')]    stemmed_content = ' '.join(stemmed_content)    return stemmed_content# Define the request body schema using Pydanticclass NewsInput(BaseModel):    title: str    paragraph: str# Root endpoint to render the form@app.get("/", response_class=HTMLResponse)async def read_form(request: Request):    return templates.TemplateResponse("index.html", {"request": request})# Prediction route@app.post("/predict")async def predict(input_data: NewsInput):    title = input_data.title    paragraph = input_data.paragraph    # Combine title and paragraph    content = title + ' ' + paragraph    # Preprocess the text    preprocessed_text = preprocess_text(content)    # Transform the text using the vectorizer    transformed_text = vectorizer.transform([preprocessed_text])    # Make a prediction using the model    prediction = model.predict(transformed_text)    # Return prediction as a response    return {"prediction": "Fake News" if prediction[0] == 1 else "Real News"}if __name__ == "__main__":    import uvicorn    uvicorn.run(app, host="0.0.0.0", port=8080)

diff --git a/models/logistic_regression_model.pkl b/models/logistic_regression_model.pkl
diff --git a/models/tfidf_vectorizer.pkl b/models/tfidf_vectorizer.pkl
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1 @@
+fastapi==0.115.2uvicorn==0.32.0joblib==1.4.2nltk==3.9.1pandas==1.1.5scikit-learn==0.24.2numpy==1.19.5rematplotlib==3.4.3seaborn==0.11.2pydantic==1.8.2

diff --git a/static/styles.css b/static/styles.css
diff --git a/templates/index.html b/templates/index.html
@@ -0,0 +1 @@
+<!DOCTYPE html><html lang="en"><head>    <meta charset="UTF-8">    <meta name="viewport" content="width=device-width, initial-scale=1.0">    <title>Fake News Prediction</title>    <link rel="stylesheet" href="/styles.css"></head><body>    <div class="container">        <h1>Fake News Prediction</h1>        <form id="newsForm" action="/predict" method="post">            <label for="title">Title:</label><br>            <input type="text" id="title" name="title" required><br>            <label for="paragraph">Paragraph:</label><br>            <textarea id="paragraph" name="paragraph" rows="5" required></textarea><br>            <button type="submit">Predict</button>        </form>        <div id="result"></div>    </div>    <script>        const form = document.getElementById('newsForm');        form.onsubmit = async (event) => {            event.preventDefault();            const formData = new FormData(form);            const response = await fetch('/predict', {                method: 'POST',                headers: {                    'Content-Type': 'application/json'                },                body: JSON.stringify({                    title: formData.get('title'),                    paragraph: formData.get('paragraph')                })            });            const result = await response.json();            document.getElementById('result').innerHTML = `<p>Prediction: ${result.prediction}</p>`;        };    </script></body></html>