Upload 2 files

src/streamlit_app.py

@@ -1,4 +1,3 @@
-import numpy as np
 import pickle
 import pandas as pd
 import streamlit as st
@@ -14,15 +13,15 @@ data = [
     {"key": "mode", "label": "Mode", "default": 0, "type": "bool"},
     {"key": "valence", "label": "Valence", "min": 0.00,
         "max": 1.00, "default": 0.48, "type": "number"},
-    {"key": "speechiness_log", "label": "Speechiness", "min": 0.00,
+    {"key": "speechiness", "label": "Speechiness", "min": 0.00,
         "max": 1.00, "default": 0.79, "type": "number"},
-    {"key": "acousticness_log", "label": "Acousticness",
-        "min": 0.00, "max": 1.00, "default": 0.24, "type": "number"},
-    {"key": "liveness_log", "label": "Liveness", "min": 0.00,
+    {"key": "acousticness", "label": "Acousticness", "min": 0.00,
+        "max": 1.00, "default": 0.34, "type": "number"},
+    {"key": "liveness", "label": "Liveness", "min": 0.00,
         "max": 1.00, "default": 0.19, "type": "number"},
-    {"key": "instrumentalness_log", "label": "Instrumentalness",
+    {"key": "instrumentalness", "label": "Instrumentalness",
         "min": 0.00, "max": 1.00, "default": 0.17, "type": "number"},
-    {"key": "duration_in_min_sg_log", "label": "Duration in seg",
+    {"key": "duration_in_min_sg", "label": "Duration in seg",
         "min": 0, "max": 1000000, "default": 317, "type": "number"},
 ]
 
@@ -52,26 +51,14 @@ response = [
 ]
 
 # LOGIC
-@st.cache_resource
-def load_model(path="./src/xgb_model.pkl"):
-    try:
-        with open(path, "rb") as f:
-            model = pickle.load(f)
-            return model
-    except FileNotFoundError:
-        st.error(
-            f"Error: Model file not found at {path}. Please ensure the model file is in the directory.")
-        return None
-    except Exception as e:
-        st.error(f"An error occurred while loading the model: {e}")
-        return None
+# @st.cache_resource
 
 
-@st.cache_resource
-def load_model_scaler(path="./src/scaler.pkl"):
+def load_model(path="xgb_classifier_pipeline.pkl"):
     try:
         with open(path, "rb") as f:
-            return pickle.load(f)
+            model = pickle.load(f)
+            return model
     except FileNotFoundError:
         st.error(
             f"Error: Model file not found at {path}. Please ensure the model file is in the directory.")
@@ -82,13 +69,13 @@ def load_model_scaler(path="./src/scaler.pkl"):
 
 
 model = load_model()
-scaler = load_model_scaler()
 input_data_original = {}
 prediction = -1
 datos_bool = []
 
 
 # VIEW
+
 # Custom CSS for styling
 st.markdown("""<style>
     .main {
@@ -240,43 +227,38 @@ with col1:
     st.markdown('<h1>Predict Music Genre</h1>', unsafe_allow_html=True)
 
     for data_point in data:
-        if data_point["type"] == "number":
-            input_data_original[data_point["key"]] = st.number_input(
-                label=data_point["label"], min_value=data_point["min"], max_value=data_point["max"], value=data_point["default"])
-        elif data_point["type"] == "bool":
-            input_data_original[data_point["key"]] = st.checkbox(
-                label=data_point["label"], value=data_point["default"])
-            datos_bool.append(data_point["key"])
+      if data_point["type"] == "number":
+        input_data_original[data_point["key"]] = st.number_input(
+            label=data_point["label"], min_value=data_point["min"], max_value=data_point["max"], value=data_point["default"])
+      elif data_point["type"] == "bool":
+        input_data_original[data_point["key"]] = st.checkbox(
+            label=data_point["label"], value=data_point["default"])
+        datos_bool.append(data_point["key"])
 
     if st.button("Predict Genre"):
-        try:
-            for key in datos_bool:
-                input_data_original[key] = int(input_data_original[key])
+      try:
+        for key in datos_bool:
+          input_data_original[key] = int(input_data_original[key])
 
-            for key in input_data_original:
-                if 'log' in key:
-                    input_data_original[key] = np.log1p(
-                        input_data_original[key])
+        input_df_model = pd.DataFrame([input_data_original])
+        input_df_model = pd.DataFrame(
+            input_df_model, columns=input_df_model.columns)
+        prediction = int(model.predict(input_df_model.head(1)))
+      except Exception as e:
+        st.error(f"An error occurred during prediction: {e}")
 
-            input_df_model = pd.DataFrame([input_data_original])
-            input_df_scaled = scaler.transform(input_df_model)
-            input_df_model = pd.DataFrame(
-                input_df_scaled, columns=input_df_model.columns)
-            prediction = int(model.predict(input_df_model)[0])
-        except Exception as e:
-            st.error(f"An error occurred during prediction: {e}")
 with col2:
-    st.markdown('<h2 class="predicted-genre-title">Predicted Genre</h2>',
-                unsafe_allow_html=True)
+  st.markdown('<h2 class="predicted-genre-title">Predicted Genre</h2>',
+              unsafe_allow_html=True)
 
-    if prediction != -1:
-        st.markdown(f"""
+  if prediction != -1:
+    st.markdown(f"""
       <div class="fixed-height-image-container">
           <img src="{response[prediction]["image"]}" alt="Imagen grande">
       </div>
     """, unsafe_allow_html=True)
 
-        st.markdown(f"""
+    st.markdown(f"""
         <div class="genre-box">
             <h3>{response[prediction]["label"]}</h3>
             <p>{response[prediction]["descripcion"]}</p>
@@ -288,8 +270,8 @@ with col2:
             <p>Pop: [Popularity: 79, Danceability: 0.80, Mode: False, Valance: 0.05, Speechines: 0.79, Acousticness: 0.48, Liveness: 0.03, Instrumentalness: 0.61, Duration in seg: 352]</p>
         </div>
     """, unsafe_allow_html=True)
-    else:
-        st.markdown("""
+  else:
+    st.markdown("""
         <div class="genre-box max-box">
             <h3>Select values and predict genre</h3>
             <h3>Ejemplos</h3>
@@ -299,4 +281,4 @@ with col2:
             <p>Alternative: [Popularity: 44, Danceability: 0.66, Mode: False, Valance: 0.48, Speechines: 0.79, Acousticness: 0.34, Liveness: 0.19, Instrumentalness: 0.17, Duration in seg: 317]</p>
             <p>Pop: [Popularity: 79, Danceability: 0.80, Mode: False, Valance: 0.05, Speechines: 0.79, Acousticness: 0.48, Liveness: 0.03, Instrumentalness: 0.61, Duration in seg: 352]</p>
         </div>
-    """, unsafe_allow_html=True)
+    """, unsafe_allow_html=True)

src/xgb_classifier_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd68dbec42d6325bc5ad316a818a307458f2c64242eee05ff327cf8b3a2dc2d9
+size 10442977