Upload app3.py

app3.py

@@ -0,0 +1,114 @@
+import streamlit as st
+import pandas as pd
+import joblib
+from preprocessText import preprocess
+from apiSearch import get_metadata
+import base64
+import requests
+# Load the model
+model = joblib.load('85pct.pkl')
+
+# Define the categories
+categories = {
+    'Film & Animation': 1,
+    'Autos & Vehicles': 2,
+    'Music': 10,
+    'Pets & Animals': 15,
+    'Sports' : 17,
+    'Short Movies' : 18,
+    'Travel & Events' : 19,
+    'Gaming' : 20,
+    'Videoblogging' : 21,
+    'People & Blogs' : 22,
+    'Comedy' : 23,
+    'Entertainment' : 24,
+    'News & Politics' : 25,
+    'Howto & Style' : 26,
+    'Education' : 27,
+    'Science & Technology' : 28,
+    'Nonprofits & Activism' : 29
+}
+
+# Create the Streamlit web application
+def main():
+    st.set_page_config(layout="wide")
+    st.title("YouTube Trend Prediction")
+    st.write("Enter the video details below:")
+
+    # Input fields
+    col1, col2, col3 = st.columns(3)
+    getTitle, getDuration, getCategory = "", 0.00, 1
+    getThumbnailUrl = ""
+    with col1:
+        url = st.text_input("URL")
+        if url:
+            metadata = get_metadata(url)
+            if not metadata.empty:
+                getTitle = metadata['title'].iloc[0]
+                getDuration = metadata['duration'].iloc[0]
+                category_id = metadata['category_id'].iloc[0]
+                getThumbnailUrl = metadata['thumbnail_link'].iloc[0]
+                getCategory = int(category_id)
+        if getThumbnailUrl is not None:
+            picture = get_picture_from_url(getThumbnailUrl)
+            if picture:
+                st.image(picture, caption='Uploaded Picture', use_column_width=True)
+    with col2:
+        title = st.text_input("Title", value=getTitle)
+        duration = st.number_input("Duration (in minutes)", min_value=0.0, value=getDuration)
+        category = st.selectbox("Category", list(categories.keys()), index=list(categories.values()).index(getCategory))
+    
+    with col3:
+        picture = st.file_uploader("Upload Picture", type=["jpg", "jpeg", "png"])
+        if picture is not None:
+            st.picture(picture, use_column_width=True)
+    # Convert category to category ID
+    categoryId = categories[category]
+    
+    # Predict button
+    if st.button("Predict"):
+        # Perform prediction
+        prediction = predict_trend(title, duration, categoryId)
+        if prediction[0] == 1:
+            st.success("This video is predicted to be a trend!")
+            st.markdown("![Alt Text](https://media.tenor.com/Cyi2zT7wcmcAAAAj/pentol-gif-eak.gif)")
+        else:
+            st.info("This video is predicted not to be a trend.")
+            st.markdown("![Alt Text](https://media.tenor.com/VYKtkKnHaUcAAAAj/quby-cute.gif)")
+    
+
+
+
+
+def get_picture_from_url(url):
+    try:
+        response = requests.get(url)
+        image_data = response.content
+        return image_data
+    except:
+        return None
+
+# Function to make predictions
+def predict_trend(title, duration, category_id):
+    duration = str(duration)
+    category_id = str(category_id)
+    clean_new_title = preprocess(title)
+    # Join the preprocessed words back into a string
+    clean_new_title_str = ' '.join(clean_new_title)
+    # Prepare the input data
+    data = {
+        'cleanTitle': [clean_new_title_str],
+        'titleLength' : [len(title)],
+        'categoryId': [category_id],
+        'duration': [duration]
+    }
+    data = pd.DataFrame(data)
+    data['categoryId'] = data['categoryId'].astype('category')
+    data['duration'] = data['duration'].astype('float64')
+    # Make the prediction
+    print(model.predict_proba(data))
+    prediction = model.predict(data)
+    return prediction
+
+if __name__ == "__main__":
+    main()