add pipeline

app.py

@@ -1,9 +1,8 @@
 import streamlit as st
+import pandas as pd
 
-from utils import csv_to_featuers_list
 from autoML import autoML
 
-
 st.set_page_config(layout="wide")
 
 # add categorical features
@@ -19,9 +18,7 @@ with st.sidebar:
 
     st.subheader('AutoML your Dataset')
 
-    csv = st.file_uploader(label='CSV file')
-    if csv != None:
-        csv = csv.name
+    csv = st.file_uploader(label='CSV file', type='csv')
     
     task = st.selectbox(label='Task', options=['Classification', 'Regression'])
 
@@ -33,7 +30,9 @@ with st.sidebar:
         metric_to_minimize_class = None
         
     if csv:
-        lst_features = csv_to_featuers_list(csv)
+        df = pd.read_csv(csv)
+        df.to_csv('datasets/temp_file.csv', index=False)
+        lst_features = df.columns
         label = st.selectbox(label='Label', options=lst_features)
     
     budget = st.text_area(label='Budget Time', value="5")
@@ -42,7 +41,7 @@ with st.sidebar:
 
 if start_but:
 
-    autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimize_reg)
+    autoML('datasets/temp_file.csv', task, budget, label, metric_to_minimize_class, metric_to_minimize_reg)
 
 
 if demo_but_class:

autoML.py

@@ -1,3 +1,4 @@
+import os
 import streamlit as st
 import pandas as pd
 import numpy as np
@@ -20,6 +21,7 @@ def autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimiz
     time.sleep(0.5)
 
     df = pd.read_csv(csv)
+    print(df)
     df_features = df[df.columns.difference([label])]
     y = df[label]
 
@@ -144,7 +146,11 @@ def autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimiz
                                                 'features importance': perm_importance["importances_mean"],
                                                 'std error': perm_importance["importances_std"]})
         
-        fig_features = px.bar(df_features_importance, x='features importance', y='features name', error_x='std error')
+        fig_features = px.bar(df_features_importance, 
+                              x='features importance', 
+                              y='features name', 
+                              error_x='std error',
+                              height=50*len(df_features_importance))
     
         st.divider()
         st.plotly_chart(fig_features, theme="streamlit")
@@ -155,4 +161,7 @@ def autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimiz
             href = f'<a href="data:file/output_model;base64,{b64}" download="automl.pkl">Download Trained Model File (.pkl)</a>'
             st.markdown(href, unsafe_allow_html=True)
 
-        download_model(automl)
+        download_model(automl)
+
+    if os.path.isfile('datasets/temp_file.csv'):
+        os.remove('datasets/temp_file.csv')