Hugging Face's logo

Spaces:
KaiquanMah
/
is_click_predictor
Configuration error

App Files Community
is_click_predictor
File size: 4,185 Bytes 
2752969
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
import streamlit as st
import pandas as pd
import joblib
from huggingface_hub import hf_hub_download

from modelConnector import ModelConnector

# ===========================
#  LOAD MODEL & DATASET
# ===========================

st.title("📊 Is Click Predictor")

# Download and load the trained model from Hugging Face
model_path = hf_hub_download(repo_id="taimax13/is_click_predictor", filename="rf_model.pkl")
rf_model = joblib.load(model_path)
st.success("✅ Model Loaded Successfully!")

# ===========================
#  LOAD DATA FROM HUGGING FACE
# ===========================

st.sidebar.header("Dataset Selection")

# # Download required dataset files
# X_test_path = hf_hub_download(repo_id="taimax13/is_click_data", filename="X_test_1st(1).csv")
# y_test_path = hf_hub_download(repo_id="taimax13/is_click_data", filename="y_test_1st.csv")
# train_data_path = hf_hub_download(repo_id="taimax13/is_click_data", filename="train_dataset_full - train_dataset_full (1).csv")

X_test_path = "HuggingFaceRepo/data/y_test_1st (1).csv"
y_test_path = "HuggingFaceRepo/data/y_test_1st.csv"
train_data_path = "HuggingFaceRepo/data/train_dataset_full - train_dataset_full.csv"


# Load datasets
X_test = pd.read_csv(X_test_path)
y_test = pd.read_csv(y_test_path, header=None)  # Ensure labels match test dataset index
train_data = pd.read_csv(train_data_path)

st.info(f"✅ Loaded datasets: **Train: {len(train_data)} rows**, **Test: {len(X_test)} rows**")



# Initialize Model Connector
model_connector = ModelConnector()

st.title("📊 Is Click Predictor - Train, Retrain, and Predict")

# ===========================
#  CHECK MODEL STATUS
# ===========================

if model_connector.model:
    st.success("✅ Model Loaded Successfully!")
else:
    st.warning("⚠ No model found. Please train one first.")

# ===========================
#  TRAIN MODEL IF NOT FOUND
# ===========================

if st.button("🚀 Train Model"):
    st.info("🔄 Training model...")
    message = model_connector.train_model()
    st.success(message)

# ===========================
#  RETRAIN MODEL
# ===========================

if st.button("🔄 Retrain Model"):
    st.info("🔄 Retraining model with latest data...")
    message = model_connector.retrain_model()
    st.success(message)


# ===========================
#  SELECT A DATA SAMPLE
# ===========================

st.sidebar.header("Select a Test Sample for Prediction")

# Merge X_test with y_test for selection (without labels affecting prediction)
X_test["actual_click"] = y_test.values

# Allow user to pick a row
selected_index = st.sidebar.selectbox("Choose a test sample index", X_test.index)
selected_row = X_test.loc[selected_index].drop("actual_click")  # Exclude actual label

# Display selected row
st.write("### Selected Data Sample:")
st.dataframe(selected_row.to_frame().T)  # Display as a table



# ===========================
#  MAKE PREDICTION & EXPORT CSV
# ===========================

if st.button("Predict Click"):
    # Convert selected row to DataFrame for model input
    input_data = selected_row.to_frame().T

    # Make prediction
    prediction = rf_model.predict(input_data)[0]

    # Add prediction to DataFrame
    input_data["is_click_predicted"] = prediction

    # Save prediction as CSV
    csv_filename = "prediction_result.csv"
    input_data.to_csv(csv_filename, index=False)

    # Display Prediction Result
    st.subheader("Prediction Result")
    if prediction == 1:
        st.success("🟢 The model predicts: **User WILL CLICK on the ad!**")
    else:
        st.warning("🔴 The model predicts: **User WILL NOT CLICK on the ad.**")

    # Provide download button for prediction result
    st.download_button(
        label="📥 Download Prediction Result",
        data=input_data.to_csv(index=False).encode("utf-8"),
        file_name="prediction_result.csv",
        mime="text/csv",
    )

st.markdown("---")
st.info("Select a test row from the **left panel**, click **'Predict Click'**, and download the prediction result as a CSV.")