start

app.py

@@ -0,0 +1,64 @@
+import gradio as gr
+from PIL import Image
+import requests
+import hopsworks
+import joblib
+import pandas as pd
+import datetime
+import os
+
+year = datetime.date.today().year
+
+project = hopsworks.login()
+fs = project.get_feature_store()
+mr = project.get_model_registry()
+model_url = f"valuation_model_v{year-1}_{year}"
+model = mr.get_model(model_url)
+model_dir = model.download()
+model = joblib.load(f"{model_dir}/valuation_model.pkl")
+scaler = joblib.load(f"{model_dir}/scaler.pkl")
+
+#Get data that has not been trained on
+fg = fs.get_or_create_feature_group(
+    name='prediction_valuation_fg',
+    version=1,
+    description='Feature group containing X_test and y_test data for model performance measurement',
+    primary_key=['player_id', 'date']  # Replace with your primary key column name(s)
+)
+
+df = fg.read()
+print(df)
+
+def valuation_predictor(goals, assists, y_cards, r_cards, 
+                    m_played, height, age, mo_left, 
+                    t_made_goals, t_conceded_goals, t_clean_sheets,
+                    pos, league):
+    
+    features_for_prediction = [
+        y_cards, r_cards, goals, assists, m_played, height, age, mo_left, t_made_goals, t_conceded_goals, t_clean_sheets, league=="La Liga", league=="League 1", league=="Premier league", league=="Serie A", league=="Bundesliga", pos=="Attack", pos=="Defender", pos=="Goalkeeper", pos=="Midfield"
+        ]
+    
+    column_names = [
+        "yellow_cards", "red_cards", "goals", "assists", "minutes_played", "height_in_cm", "age", "months_left", "own_goals", "opponent_goals", "clean_sheets", "league_es1","league_fr1", "league_gb1","league_it1","league_l1", "position_attack","position_defender", "position_goalkeeper","position_midfield"
+        ]
+    
+    
+    # Create DataFrame from the input features
+    X_predict = pd.DataFrame([features_for_prediction], columns=column_names)
+    # Apply the scaler to the relevant columns
+    scaled_columns = ['age', 'height_in_cm', 'minutes_played']
+    X_predict[scaled_columns] = scaler.transform(X_predict[scaled_columns])
+    estimated_valuation = model.predict(X_predict)
+    
+    # Reformatting to the nearest thousand with commas
+    formatted_output_thousand = f"{round(estimated_valuation[0], -3):,} EUR"
+    return formatted_output_thousand
+
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    with gr.Row():
+        gr.Label(value="Latest predictions", show_label=False)
+
+        
+            
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+requests
+hopsworks
+joblib
+pandas
+scikit-learn