Spaces:
Sleeping
Sleeping
| # app.py | |
| import streamlit as st | |
| import pickle | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns | |
| # Load dataset | |
| df = pd.read_csv("/app/src/dataset_Facebook.csv", sep=";") | |
| # Load trained regression model (pipeline) | |
| with open("/app/src/regression_model.pkl", "rb") as f: | |
| model = pickle.load(f) | |
| st.set_page_config(page_title="Facebook Post Reach Prediction", layout="wide") | |
| # Sidebar navigation | |
| st.sidebar.title("Navigation") | |
| menu = [ | |
| "Introduction", | |
| "Problem Statement", | |
| "Data Collection", | |
| "EDA", | |
| "Feature Engineering", | |
| "Model Building", | |
| "Deployment" | |
| ] | |
| choice = st.sidebar.radio("Go to", menu) | |
| # Page 1: Introduction | |
| if choice == "Introduction": | |
| st.title("Facebook Post Reach Prediction using Regression") | |
| st.write(""" | |
| This project predicts the **Lifetime Post Total Reach** of Facebook posts | |
| using machine learning regression. | |
| By analyzing engagement metrics (likes, shares, comments, impressions, etc.), | |
| as well as temporal and categorical features, we can estimate how many people | |
| a post is likely to reach. | |
| Navigate through the sections to explore the dataset, insights, | |
| model building process, and live predictions. | |
| """) | |
| # Page 2: Problem Statement | |
| elif choice == "Problem Statement": | |
| st.title("Problem Statement") | |
| st.write(""" | |
| Social media managers often struggle to estimate how far a post will reach | |
| before it is published. | |
| **Goal:** Build a regression model that predicts the | |
| **Lifetime Post Total Reach** of a Facebook post using historical data. | |
| **Why it matters:** | |
| - Optimize posting time and strategy | |
| - Anticipate engagement levels | |
| - Improve ad budget allocation | |
| """) | |
| # Page 3: Data Collection | |
| elif choice == "Data Collection": | |
| st.title("Data Collection") | |
| st.write("Here’s a preview of the dataset used:") | |
| st.dataframe(df.head()) | |
| st.markdown(""" | |
| **Key Features:** | |
| - `page_total_likes` — Page followers at posting time | |
| - `type` — Post type (Photo, Status, Link, Video) | |
| - `category` — Category of the post | |
| - `post_month`, `post_weekday`, `post_hour` — Temporal features | |
| - `paid` — Boosted (1) or Organic (0) | |
| - `total_post_impressions`, `lifetime_engaged_users`, `lifetime_post_consumers`, | |
| `lifetime_post_consumptions`, `impressions_from_likers`, | |
| `reach_from_likers`, `likers_engaged_with_post` | |
| - Engagement metrics: `comments`, `likes`, `shares`, `total_interactions` | |
| - **Target variable:** `Lifetime Post Total Reach` | |
| """) | |
| # Page 4: EDA | |
| elif choice == "EDA": | |
| st.title("Exploratory Data Analysis (EDA)") | |
| # Distribution of target | |
| fig1, ax = plt.subplots(figsize=(6, 4)) | |
| sns.histplot(df["Lifetime Post Total Reach"], bins=30, kde=True, ax=ax) | |
| ax.set_title("Distribution of Post Reach") | |
| st.pyplot(fig1) | |
| plt.close(fig1) | |
| # Correlation heatmap | |
| fig2, ax = plt.subplots(figsize=(10, 6)) | |
| corr = df.corr(numeric_only=True) | |
| sns.heatmap(corr, cmap="coolwarm", annot=False, ax=ax) | |
| ax.set_title("Correlation Heatmap") | |
| st.pyplot(fig2) | |
| plt.close(fig2) | |
| st.markdown(""" | |
| **Insights:** | |
| - Higher likes, shares, and comments correlate strongly with reach. | |
| - Paid posts generally achieve higher reach. | |
| - Some temporal patterns are visible (e.g., posting time/weekday). | |
| """) | |
| # Page 5: Feature Engineering | |
| elif choice == "Feature Engineering": | |
| st.title("Feature Engineering") | |
| st.markdown(""" | |
| - Missing values handled in categorical and numerical features | |
| - `type` encoded using OneHotEncoder | |
| - Numeric features scaled using StandardScaler | |
| - Combined into a **ColumnTransformer** pipeline | |
| - Train-test split performed for unbiased evaluation | |
| """) | |
| # Page 6: Model Building | |
| elif choice == "Model Building": | |
| st.title("Model Building") | |
| st.markdown(""" | |
| - Algorithm: **KNeighborsRegressor** | |
| - Preprocessing included OneHotEncoding + Scaling | |
| - Model trained on full feature set of Facebook post data | |
| - Evaluation metrics: | |
| - **R² Score** | |
| - **Mean Squared Error (MSE)** | |
| Final model saved as `regression_model.pkl` and used for predictions in this app. | |
| """) | |
| # Page 7: Deployment | |
| elif choice == "Deployment": | |
| st.title("Deployment") | |
| st.write("Fill in the details below to predict **Lifetime Post Reach**:") | |
| # Inputs for all required features | |
| page_total_likes = st.number_input("Page Total Likes", min_value=0, step=100) | |
| post_type = st.selectbox("Post Type", ["Photo", "Status", "Link", "Video"]) | |
| category = st.selectbox("Category", [1, 2, 3]) | |
| post_month = st.selectbox("Post Month", list(range(1, 13))) | |
| post_weekday = st.selectbox("Post Weekday (1=Sun ... 7=Sat)", list(range(1, 8))) | |
| post_hour = st.slider("Post Hour", 0, 23, 12) | |
| paid = st.selectbox("Paid Promotion", [0, 1]) | |
| total_post_impressions = st.number_input("Total Post Impressions", min_value=0, step=100) | |
| lifetime_engaged_users = st.number_input("Lifetime Engaged Users", min_value=0, step=10) | |
| lifetime_post_consumers = st.number_input("Lifetime Post Consumers", min_value=0, step=10) | |
| lifetime_post_consumptions = st.number_input("Lifetime Post Consumptions", min_value=0, step=10) | |
| impressions_from_likers = st.number_input("Impressions from Likers", min_value=0, step=10) | |
| reach_from_likers = st.number_input("Reach from Likers", min_value=0, step=10) | |
| likers_engaged_with_post = st.number_input("Likers Engaged with Post", min_value=0, step=1) | |
| comments = st.number_input("Comments", min_value=0, step=1) | |
| likes = st.number_input("Likes", min_value=0, step=1) | |
| shares = st.number_input("Shares", min_value=0, step=1) | |
| total_interactions = st.number_input("Total Interactions", min_value=0, step=1) | |
| if st.button("Predict Reach"): | |
| input_df = pd.DataFrame([[ | |
| page_total_likes, post_type, category, post_month, post_weekday, post_hour, paid, | |
| total_post_impressions, lifetime_engaged_users, lifetime_post_consumers, | |
| lifetime_post_consumptions, impressions_from_likers, reach_from_likers, | |
| likers_engaged_with_post, comments, likes, shares, total_interactions | |
| ]], columns=[ | |
| 'page_total_likes', 'type', 'category', 'post_month', 'post_weekday', | |
| 'post_hour', 'paid', 'total_post_impressions', 'lifetime_engaged_users', | |
| 'lifetime_post_consumers', 'lifetime_post_consumptions', | |
| 'impressions_from_likers', 'reach_from_likers', 'likers_engaged_with_post', | |
| 'comments', 'likes', 'shares', 'total_interactions' | |
| ]) | |
| prediction = model.predict(input_df)[0] | |
| st.success(f"Estimated Post Reach: {prediction:.0f} users") | |