Initial commit with LFS model

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/AdClickPredictor.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,13 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="streamlit" />
+          <option value="pandas" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/AdClickPredictor.iml" filepath="$PROJECT_DIR$/.idea/AdClickPredictor.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

app/app.py

@@ -0,0 +1,59 @@
+import streamlit as st
+import pandas as pd
+import joblib
+import json
+import os
+
+ROOT = os.path.dirname(os.path.abspath(__file__))
+if os.path.basename(ROOT) == "app":
+    ROOT = os.path.dirname(ROOT)
+METRICS_DIR = os.path.join(ROOT, "metrics")
+MODEL_PATH = os.path.join(ROOT, "src", "model.pkl")
+DATA_PATH = os.path.join(ROOT, "data", "ad_click_dataset.csv")
+
+model = joblib.load(MODEL_PATH)
+with open(os.path.join(METRICS_DIR, 'metrics.json')) as f:
+    metrics = json.load(f)
+
+df = pd.read_csv(DATA_PATH)
+cat_options = {col: df[col].dropna().unique().tolist() for col in df.columns if col not in ['id', 'full_name', 'click', 'age']}
+
+st.title("Ad Click Predictor")
+st.markdown(
+    "Wprowadź dane użytkownika i sprawdź, czy kliknie w reklamę!<br>"
+    "<sup>Model został wybrany automatycznie na podstawie walidacji krzyżowej spośród Random Forest, Logistic Regression oraz Gradient Boosting (Pipeline).</sup>",
+    unsafe_allow_html=True,
+)
+
+age = st.slider("Wiek użytkownika", 18, 64, 30)
+gender = st.selectbox("Płeć", cat_options['gender'])
+device_type = st.selectbox("Typ urządzenia", cat_options['device_type'])
+ad_position = st.selectbox("Pozycja reklamy", cat_options['ad_position'])
+browsing_history = st.selectbox("Poprzednia aktywność", cat_options['browsing_history'])
+time_of_day = st.selectbox("Pora dnia", cat_options['time_of_day'])
+
+user_input = pd.DataFrame([{
+    "age": age,
+    "gender": gender,
+    "device_type": device_type,
+    "ad_position": ad_position,
+    "browsing_history": browsing_history,
+    "time_of_day": time_of_day
+}])
+
+if st.button("Sprawdź czy użytkownik kliknie w reklamę"):
+    proba = model.predict_proba(user_input)[0][1]
+    st.success("Kliknie!" if proba > 0.5 else "Nie kliknie.")
+    st.markdown(f"**Prawdopodobieństwo kliknięcia:** `{proba:.2%}`")
+
+st.markdown("---")
+st.markdown("#### Wybrany model (na podstawie walidacji krzyżowej):")
+st.write(f"- Model: `{metrics['best_model']}`")
+st.write(f"- Średni F1-score (cross-val): `{metrics['cv_f1_score']:.2%}`")
+
+st.markdown("#### Wyniki metryk na zbiorze testowym:")
+st.write(f"- Accuracy: `{metrics['accuracy']:.2%}`")
+st.write(f"- F1-score: `{metrics['f1_score']:.2%}`")
+
+st.markdown("#### Macierz pomyłek (Confusion Matrix):")
+st.image(os.path.join(METRICS_DIR, 'confusion_matrix.png'))

app/requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+pandas
+joblib
+scikit-learn

metrics/classification_report.txt

@@ -0,0 +1,8 @@
+              precision    recall  f1-score   support
+
+           0       0.74      0.14      0.24       700
+           1       0.68      0.97      0.80      1300
+
+    accuracy                           0.68      2000
+   macro avg       0.71      0.56      0.52      2000
+weighted avg       0.70      0.68      0.60      2000

metrics/metrics.json

@@ -0,0 +1 @@
+{"accuracy": 0.6825, "f1_score": 0.7992412266835283, "best_model": "GradientBoosting", "cv_f1_score": 0.8046270813874387}

src/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1da853e8732b81b3ce8a71e0c9d0e46ac46361e0e085c51bcce01664386239
+size 275892