update

app.py

@@ -1,4 +1,5 @@
 import os
+import mlflow 
 import streamlit as st
 import pandas as pd
 from pycaret.classification import *
@@ -6,41 +7,33 @@ from pycaret.classification import *
 os.environ['MLFLOW_TRACKING_USERNAME'] = 'fandanabil1379'
 os.environ['MLFLOW_TRACKING_PASSWORD'] = 'dadc32f6246f307c2fe4928f3074068f628b79ba'
 
-# @st.cache_data
+# load model
+mlflow.set_tracking_uri('https://dagshub.com/fandanabil1379/loan_prediction.mlflow')
+model_name = "v1.0.1"
+stage = "Production"
+model = mlflow.sklearn.load_model(f"models:/{model_name}/{stage}")
+
+@st.cache_data
 def convert_df(df):
    return df.to_csv(index=False).encode('utf-8')
 
-# init
-st.set_page_config(page_title="Loan Default Prediction App")
-st.title('Loan Default Prediction')
+def run():
+   # init
+   st.set_page_config(page_title="Loan Default Prediction App")
+   st.title('Loan Default Prediction')
 
-# load model
-def load_model():
-   import mlflow 
-   mlflow.set_tracking_uri('https://dagshub.com/fandanabil1379/loan_prediction.mlflow')
-   model_name = "v1.0.1"
-   stage = "Production"
-   loaded_model = mlflow.sklearn.load_model(f"models:/{model_name}/{stage}")
-   return loaded_model
-
-# @st.cache_data(experimental_allow_widgets=True)
-def prediction():
-   # load data
    uploaded_file = st.file_uploader("Choose a file", type={"csv"})
    if uploaded_file is not None:
       # do prediction
-      df = pd.read_csv(uploaded_file)
-      model = load_model()
-      prediction = predict_model(model, df).drop(columns='Unnamed: 0')
-      return prediction
-   
-result = prediction()
+      data = pd.read_csv(uploaded_file)
+      prediction = predict_model(model, data)
 
-# show the result
-st.write(result)
+      # show the result
+      st.write(prediction)
 
-# download the result
-# csv = convert_df(result)
-# if st.download_button('Download Prediction', csv, 'prediction.csv'):
-#    st.write('Thanks for downloading!')
+      # download the result
+      csv = convert_df(result)
+      if st.download_button('Download Prediction', csv, 'prediction.csv'):
+         st.write('Thanks for downloading!')
 
+run()

logs.log

@@ -238,3 +238,49 @@ Feature names unseen at fit time:
 2023-08-04 07:30:33,393:INFO:Preloading libraries
 2023-08-04 07:30:33,395:INFO:Set up data.
 2023-08-04 07:30:33,403:INFO:Set up index.
+2023-08-08 22:18:02,376:WARNING:
+'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
+2023-08-08 22:18:02,376:WARNING:
+'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
+2023-08-08 22:18:02,376:WARNING:
+'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
+2023-08-08 22:18:02,376:WARNING:
+'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
+2023-08-08 22:26:27,519:INFO:Initializing predict_model()
+2023-08-08 22:26:27,519:INFO:predict_model(self=<pycaret.classification.oop.ClassificationExperiment object at 0x285b30f70>, estimator=Pipeline(memory=FastMemory(location=/var/folders/vh/81ldn_315vdf1b2_lnntkb080000gn/T/joblib),
+         steps=[('combine',
+                 TransformerWrapper(transformer=TransformerWrapper(include=['ed'],
+                                                                   transformer=Combine()))),
+                ('remove outlier',
+                 TransformerWrapper(transformer=TransformerWrapper(transformer=RemoveOutliers(random_state=42)))),
+                ('normalize',
+                 TransformerWrapper(transformer=TransformerWrapper(exclude=['ed',
+                                                                            'age'],
+                                                                   transformer=RobustScaler()))),
+                ('actual_estimator',
+                 LogisticRegression(C=8.956999999999999,
+                                    class_weight='balanced', max_iter=1000,
+                                    random_state=42))]), probability_threshold=None, encoded_labels=False, raw_score=False, round=4, verbose=True, ml_usecase=None, preprocess=True, encode_labels=<function _SupervisedExperiment.predict_model.<locals>.encode_labels at 0x2857929d0>)
+2023-08-08 22:26:27,519:INFO:Checking exceptions
+2023-08-08 22:26:27,519:INFO:Preloading libraries
+2023-08-08 22:26:27,522:INFO:Set up data.
+2023-08-08 22:26:27,534:INFO:Set up index.
+2023-08-08 22:27:05,991:INFO:Initializing predict_model()
+2023-08-08 22:27:05,992:INFO:predict_model(self=<pycaret.classification.oop.ClassificationExperiment object at 0x16e1b5100>, estimator=Pipeline(memory=FastMemory(location=/var/folders/vh/81ldn_315vdf1b2_lnntkb080000gn/T/joblib),
+         steps=[('combine',
+                 TransformerWrapper(transformer=TransformerWrapper(include=['ed'],
+                                                                   transformer=Combine()))),
+                ('remove outlier',
+                 TransformerWrapper(transformer=TransformerWrapper(transformer=RemoveOutliers(random_state=42)))),
+                ('normalize',
+                 TransformerWrapper(transformer=TransformerWrapper(exclude=['ed',
+                                                                            'age'],
+                                                                   transformer=RobustScaler()))),
+                ('actual_estimator',
+                 LogisticRegression(C=8.956999999999999,
+                                    class_weight='balanced', max_iter=1000,
+                                    random_state=42))]), probability_threshold=None, encoded_labels=False, raw_score=False, round=4, verbose=True, ml_usecase=None, preprocess=True, encode_labels=<function _SupervisedExperiment.predict_model.<locals>.encode_labels at 0x16e1c3550>)
+2023-08-08 22:27:05,992:INFO:Checking exceptions
+2023-08-08 22:27:05,992:INFO:Preloading libraries
+2023-08-08 22:27:05,992:INFO:Set up data.
+2023-08-08 22:27:05,998:INFO:Set up index.