Update app.py

app.py

@@ -52,137 +52,60 @@ max_attempts = 5
 
 upload_file = st.file_uploader("Upload your file. Accepted file formats include: .csv, .xlsx", type=['csv', 'xlsx'])
 
-
 if upload_file is not None:
     file_extension = upload_file.name.split('.')[-1].lower()
-    if file_extension == 'csv':
-        try:
-            df = pd.read_csv(upload_file, na_filter=False)
-            if df.isnull().values.any():
-                st.error("Error: The CSV file contains missing values.")
-                st.stop()
-            else:
-                new_columns = [f'column_{i+1}' for i in range(len(df.columns))]
-                df.columns = new_columns
-                
-                all_columns = df.columns.tolist()
-                st.subheader("Select columns for the Tree Map", divider="blue")
-                parent_column = st.selectbox("Select the parent column:", all_columns)
-                value_column = st.selectbox("Select the value column:", all_columns)
-                
-            if parent_column and value_column:
-                if parent_column == value_column:
-                    st.warning("Warning: You have selected the same column for both the parent and value column. Please select two different columns from your data.")
-                elif parent_column and value_column:
-                    path_columns = [px.Constant("all"), parent_column, value_column]
-                    fig = px.treemap(df,
-                         path=path_columns)
-
-                    fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
-                    st.subheader("Tree map", divider="red")
-                    st.plotly_chart(fig)
-                    
-                    
-                    st.session_state.df = df  
-        except pd.errors.ParserError:
-            st.error("Error: The CSV file is not readable or is incorrectly formatted.")
-            st.stop()
-        except UnicodeDecodeError:
-            st.error("Error: The CSV file could not be decoded.")
+    try:
+        if file_extension == 'csv':
+            df_original = pd.read_csv(upload_file, na_filter=False)
+        elif file_extension == 'xlsx':
+            df_original = pd.read_excel(upload_file, na_filter=False)
+        else:
+            st.warning("Unsupported file type.")
             st.stop()
-        except Exception as e:
-            st.error(f"An unexpected error occurred while reading CSV: {e}")
+
+        if df_original.isnull().values.any():
+            st.error("Error: The file contains missing values.")
             st.stop()
-    elif file_extension == 'xlsx':
-        try:
-            df = pd.read_excel(upload_file, na_filter=False)
-            
-            if df.isnull().values.any():
-                st.error("Error: The Excel file contains missing values.")
-                st.stop()
-            else:
-                new_columns = [f'column_{i+1}' for i in range(len(df.columns))]
-                df.columns = new_columns
-                
-                all_columns = df.columns.tolist()
-                st.subheader("Select columns for the Tree Map", divider="blue")
-                parent_column = st.selectbox("Select the parent column:", all_columns)
-                value_column = st.selectbox("Select the value column:", all_columns)
-                
+        else:
+            st.session_state.df_original = df_original  # Store the original dataframe
+
+            all_columns = df_original.columns.tolist()
+            st.subheader("Select columns for the Tree Map", divider="blue")
+            parent_column = st.selectbox("Select the parent column:", all_columns)
+            value_column = st.selectbox("Select the value column:", all_columns)
+
             if parent_column and value_column:
                 if parent_column == value_column:
                     st.warning("Warning: You have selected the same column for both the parent and value column. Please select two different columns from your data.")
-                elif parent_column and value_column:
+                else:
+                    df_treemap = df_original.copy()  # Create a copy for treemap
                     path_columns = [px.Constant("all"), parent_column, value_column]
-                    fig = px.treemap(df,
-                         path=path_columns)
-
+                    fig = px.treemap(df_treemap,
+                                     path=path_columns)
                     fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
                     st.subheader("Tree map", divider="red")
                     st.plotly_chart(fig)
-                    
-                    
-                    st.session_state.df = df  
-                         
-        except ValueError:
-            st.error("Error: The Excel file is not readable or is incorrectly formatted.")
-            st.stop()
-        except Exception as e:
-            st.error(f"An unexpected error occurred while reading Excel: {e}")
-            st.stop()
-    else:
-        st.warning("Unsupported file type.")
-        st.stop()
-
 
+            st.subheader("Uploaded Data", divider="green")
+            st.dataframe(df_original, key="uploaded_dataframe")
+            st.write(f"_Number of rows_: {df_original.shape[0]}")
+            st.write(f"_Number of columns_: {df_original.shape[1]}")
 
+    except pd.errors.ParserError:
+        st.error("Error: The CSV file is not readable or is incorrectly formatted.")
+        st.stop()
+    except UnicodeDecodeError:
+        st.error("Error: The CSV file could not be decoded.")
+        st.stop()
+    except ValueError:
+        st.error("Error: The Excel file is not readable or is incorrectly formatted.")
+        st.stop()
+    except Exception as e:
+        st.error(f"An unexpected error occurred: {e}")
+        st.stop()
 
- 
 st.divider()
-
-if upload_file is not None:
-    file_extension = upload_file.name.split('.')[-1].lower()
-    if file_extension == 'csv':
-        try:
-            df = pd.read_csv(upload_file, na_filter=False)
-            if df.isnull().values.any():
-                st.error("Error: The CSV file contains missing values.")
-                st.stop()
-            else:
-                st.dataframe(df, key="csv_dataframe")
-                st.write("_number of rows_", df.shape[0])
-                st.write("_number of columns_", df.shape[1])
-                st.session_state.df = df  
-        except pd.errors.ParserError:
-            st.error("Error: The CSV file is not readable or is incorrectly formatted.")
-            st.stop()
-        except UnicodeDecodeError:
-            st.error("Error: The CSV file could not be decoded.")
-            st.stop()
-        except Exception as e:
-            st.error(f"An unexpected error occurred while reading CSV: {e}")
-            st.stop()
-    elif file_extension == 'xlsx':
-        try:
-            df = pd.read_excel(upload_file, na_filter=False)
-            
-            if df.isnull().values.any():
-                st.error("Error: The Excel file contains missing values.")
-                st.stop()
-            else:
-                st.dataframe(df, key="excel_dataframe")
-                st.write("_number of rows_", df.shape[0])
-                st.write("_number of columns_", df.shape[1])
-                st.session_state.df = df  
-        except ValueError:
-            st.error("Error: The Excel file is not readable or is incorrectly formatted.")
-            st.stop()
-        except Exception as e:
-            st.error(f"An unexpected error occurred while reading Excel: {e}")
-            st.stop()
-    else:
-        st.warning("Unsupported file type.")
-        st.stop()
+     
 
 def clear_question():
     st.session_state["question"] = ""