Upload appStore_target.py

appStore/appStore_target.py

@@ -0,0 +1,397 @@
+# set path
+import glob, os, sys; 
+sys.path.append('../utils')
+
+#import needed libraries
+import seaborn as sns
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import streamlit as st
+from st_aggrid import AgGrid
+from utils.target_classifier import load_targetClassifier, target_classification 
+import logging
+logger = logging.getLogger(__name__)
+from utils.config import get_classifier_params
+from io import BytesIO
+import xlsxwriter
+import plotly.express as px
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,
+    is_list_like)
+
+# Declare all the necessary variables
+classifier_identifier = 'target'
+params  = get_classifier_params(classifier_identifier)
+
+## Labels dictionary ###
+_lab_dict = {
+            'NEGATIVE':'NO TARGET INFO',
+            'TARGET':'TARGET',
+            }
+
+# @st.cache_data
+def to_excel(df):
+    # df['Target Validation'] = 'No'
+    # df['Netzero Validation'] = 'No'
+    # df['GHG Validation'] = 'No'
+    # df['Adapt-Mitig Validation'] = 'No'
+    # df['Sector'] = 'No'
+    len_df = len(df)
+    output = BytesIO()
+    writer = pd.ExcelWriter(output, engine='xlsxwriter')
+    df.to_excel(writer, index=False, sheet_name='rawdata')
+    if 'target_hits' in st.session_state:
+        target_hits = st.session_state['target_hits']
+        if 'keep' in target_hits.columns:
+
+            target_hits = target_hits[target_hits.keep == True]
+            target_hits = target_hits.reset_index(drop=True)
+            target_hits.drop(columns = ['keep'], inplace=True)
+            target_hits.to_excel(writer,index=False,sheet_name = 'Target')
+        else:
+
+            target_hits = target_hits.sort_values(by=['Target Score'], ascending=False)
+            target_hits = target_hits.reset_index(drop=True)
+            target_hits.to_excel(writer,index=False,sheet_name = 'Target')
+
+    else:
+        target_hits = df[df['Target Label'] == True]
+        target_hits.drop(columns=['Target Label','Netzero Score','GHG Score','Action Label',
+                                'Action Score','Policies_Plans Label','Indicator Label',
+                                'Policies_Plans Score','Conditional Score'],inplace=True)
+        target_hits = target_hits.sort_values(by=['Target Score'], ascending=False)
+        target_hits = target_hits.reset_index(drop=True)
+        target_hits.to_excel(writer,index=False,sheet_name = 'Target')
+
+
+    if 'action_hits' in st.session_state:
+        action_hits = st.session_state['action_hits']
+        if 'keep' in action_hits.columns:
+            action_hits = action_hits[action_hits.keep == True]
+            action_hits = action_hits.reset_index(drop=True)
+            action_hits.drop(columns = ['keep'], inplace=True)
+            action_hits.to_excel(writer,index=False,sheet_name = 'Action')  
+        else:
+            action_hits = action_hits.sort_values(by=['Action Score'], ascending=False)
+            action_hits = action_hits.reset_index(drop=True)
+            action_hits.to_excel(writer,index=False,sheet_name = 'Action') 
+    else:
+        action_hits = df[df['Action Label'] == True]
+        action_hits.drop(columns=['Target Label','Target Score','Netzero Score',
+                                'Netzero Label','GHG Label',
+                                'GHG Score','Action Label','Policies_Plans Label',
+                                'Policies_Plans Score','Conditional Score'],inplace=True)
+        action_hits = action_hits.sort_values(by=['Action Score'], ascending=False)
+        action_hits = action_hits.reset_index(drop=True)
+        action_hits.to_excel(writer,index=False,sheet_name = 'Action') 
+            
+    # hits = hits.drop(columns = ['Target Score','Netzero Score','GHG Score'])
+    workbook = writer.book
+    # worksheet = writer.sheets['Sheet1']
+    # worksheet.data_validation('L2:L{}'.format(len_df), 
+    #                           {'validate': 'list', 
+    #                            'source': ['No', 'Yes', 'Discard']})
+    # worksheet.data_validation('M2:L{}'.format(len_df), 
+    #                           {'validate': 'list', 
+    #                            'source': ['No', 'Yes', 'Discard']})
+    # worksheet.data_validation('N2:L{}'.format(len_df), 
+    #                           {'validate': 'list', 
+    #                            'source': ['No', 'Yes', 'Discard']})
+    # worksheet.data_validation('O2:L{}'.format(len_df), 
+    #                           {'validate': 'list', 
+    #                            'source': ['No', 'Yes', 'Discard']})
+    # worksheet.data_validation('P2:L{}'.format(len_df), 
+    #                           {'validate': 'list', 
+    #                            'source': ['No', 'Yes', 'Discard']})                                                                                                         
+    writer.save()
+    processed_data = output.getvalue()
+    return processed_data
+
+def app():
+    ### Main app code ###
+    with st.container():
+        if 'key0' in st.session_state:
+            df = st.session_state.key0
+
+            #load Classifier
+            classifier = load_targetClassifier(classifier_name=params['model_name'])
+            st.session_state['{}_classifier'.format(classifier_identifier)] = classifier
+            if len(df) > 100:
+                warning_msg = ": This might take sometime, please sit back and relax."
+            else:
+                warning_msg = ""
+                
+            df  = target_classification(haystack_doc=df,
+                                    threshold= params['threshold'])
+            st.session_state.key1 = df
+
+def filter_for_tracs(df):
+    sector_list = ['Transport','Energy','Economy-wide']
+    df['check'] = df['Sector Label'].apply(lambda x: any(i in x for i in sector_list))
+    df = df[df.check == True].reset_index(drop=True)
+    df['Sector Label'] = df['Sector Label'].apply(lambda x: [i for i in x if i in sector_list])
+    df.drop(columns = ['check'],inplace=True)
+    return df
+
+def target_display():
+    if  'key1' in st.session_state:
+        df = st.session_state.key1   
+        st.caption(""" **{}** is splitted into **{}** paragraphs/text chunks."""\
+                      .format(os.path.basename(st.session_state['filename']),
+                             len(df)))         
+        hits  = df[df['Target Label'] == 'TARGET'].reset_index(drop=True)
+        range_val = min(5,len(hits))
+        if range_val !=0:
+            # collecting some statistics
+            count_target = sum(hits['Target Label'] == 'TARGET')
+            count_netzero = sum(hits['Netzero Label'] == 'NETZERO TARGET')
+            count_ghg = sum(hits['GHG Label'] == 'GHG')
+            count_transport = sum([True if 'Transport' in x else False 
+                              for x in hits['Sector Label']])
+
+            c1, c2 = st.columns([1,1])
+            with c1:
+                st.write('**Target Paragraphs**: `{}`'.format(count_target))
+                st.write('**NetZero Related Paragraphs**: `{}`'.format(count_netzero))
+            with c2:
+                st.write('**GHG Target Related Paragraphs**: `{}`'.format(count_ghg))
+                st.write('**Transport Related Paragraphs**: `{}`'.format(count_transport))
+            # st.write('-------------------')    
+            hits.drop(columns=['Target Label','Netzero Score','GHG Score','Action Label',
+                                'Action Score','Policies_Plans Label','Indicator Label',
+                                'Policies_Plans Score','Conditional Score'],inplace=True)
+            hits = hits.sort_values(by=['Target Score'], ascending=False)
+            hits = hits.reset_index(drop=True)
+
+            # netzerohit = hits[hits['Netzero Label'] == 'NETZERO']
+            # if not netzerohit.empty:
+            #     netzerohit = netzerohit.sort_values(by = ['Netzero Score'], ascending = False)
+            #     # st.write('-------------------')
+            #     # st.markdown("###### Netzero paragraph ######")
+            #     st.write('**Netzero paragraph** `page {}`: {}'.format(netzerohit.iloc[0]['page'],
+            #                     netzerohit.iloc[0]['text'].replace("\n", " ")))                        
+            #     st.write("")
+            # else:
+            #     st.info("🤔 No Netzero paragraph found")
+
+        #     # st.write("**Result {}** `page {}` (Relevancy Score: {:.2f})'".format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Relevancy'])")
+        #     st.write('-------------------')
+        #     st.markdown("###### Top few Target Classified paragraph/text results ######")
+        #     range_val = min(5,len(hits))
+        #     for i in range(range_val):
+        #         # the page number reflects the page that contains the main paragraph 
+        #         # according to split limit, the overlapping part can be on a separate page
+        #         st.write('**Result {}** (Relevancy Score: {:.2f}): `page {}`, `Sector: {}`,\
+        #                     `GHG: {}`, `Adapt-Mitig :{}`'\
+        #             .format(i+1,hits.iloc[i]['Relevancy'],
+        #                     hits.iloc[i]['page'], hits.iloc[i]['Sector Label'],
+        #                     hits.iloc[i]['GHG Label'],hits.iloc[i]['Adapt-Mitig Label']))                        
+        #         st.write("\t Text: \t{}".format(hits.iloc[i]['text'].replace("\n", " ")))
+        #     hits = hits.reset_index(drop =True)
+            st.write('----------------')
+
+
+            st.caption("Filter table to select rows to keep for Target category")
+            hits = filter_for_tracs(hits)
+            convert_type = {'Netzero Label': 'category',
+                            'Conditional Label':'category',
+                            'GHG Label':'category',
+                            }
+            hits = hits.astype(convert_type)
+            filter_dataframe(hits)
+            
+            # filtered_df = filtered_df[filtered_df.keep == True]
+            # st.write('Explore the data')
+            # AgGrid(hits)
+            
+            
+            with st.sidebar:
+                st.write('-------------')
+                df_xlsx = to_excel(df)
+                st.download_button(label='📥 Download Result',
+                            data=df_xlsx ,
+                            file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx')
+
+# st.write(
+#     """This app accomodates the blog [here](https://blog.streamlit.io/auto-generate-a-dataframe-filtering-ui-in-streamlit-with-filter_dataframe/)
+#     and walks you through one example of how the Streamlit
+#     Data Science Team builds add-on functions to Streamlit.
+#     """
+# )
+
+
+def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Adds a UI on top of a dataframe to let viewers filter columns
+
+    Args:
+        df (pd.DataFrame): Original dataframe
+
+    Returns:
+        pd.DataFrame: Filtered dataframe
+    """
+    modify = st.checkbox("Add filters")
+
+    if not modify:
+        st.session_state['target_hits'] = df
+        return 
+
+
+    # df = df.copy()
+    # st.write(len(df))
+
+    # Try to convert datetimes into a standard format (datetime, no timezone)
+    # for col in df.columns:
+    #     if is_object_dtype(df[col]):
+    #         try:
+    #             df[col] = pd.to_datetime(df[col])
+    #         except Exception:
+    #             pass
+
+    #     if is_datetime64_any_dtype(df[col]):
+    #         df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        cols = list(set(df.columns) -{'page','Extracted Text'})
+        cols.sort()
+        to_filter_columns = st.multiselect("Filter dataframe on", cols
+                                )
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            left.write("↳")
+            # Treat columns with < 10 unique values as categorical
+            if is_categorical_dtype(df[column]):
+                # st.write(type(df[column][0]), column)
+                user_cat_input = right.multiselect(
+                    f"Values for {column}",
+                    df[column].unique(),
+                    default=list(df[column].unique()),
+                )
+                df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Values for {column}",
+                    _min,
+                    _max,
+                    (_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            elif is_list_like(df[column]) & (type(df[column][0]) == list) :
+                list_vals = set(x for lst in df[column].tolist() for x in lst)
+                user_multi_input = right.multiselect(
+                    f"Values for {column}",
+                    list_vals,
+                    default=list_vals,
+                )   
+                df['check'] = df[column].apply(lambda x: any(i in x for i in user_multi_input))
+                df = df[df.check == True]
+                df.drop(columns = ['check'],inplace=True)
+            
+                # df[df[column].between(*user_num_input)]
+            # elif is_datetime64_any_dtype(df[column]):
+            #     user_date_input = right.date_input(
+            #         f"Values for {column}",
+            #         value=(
+            #             df[column].min(),
+            #             df[column].max(),
+            #         ),
+            #     )
+            #     if len(user_date_input) == 2:
+            #         user_date_input = tuple(map(pd.to_datetime, user_date_input))
+            #         start_date, end_date = user_date_input
+            #         df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                user_text_input = right.text_input(
+                    f"Substring or regex in {column}",
+                )
+                if user_text_input:
+                    df = df[df[column].str.lower().str.contains(user_text_input)]
+            
+            df = df.reset_index(drop=True)
+        
+        st.session_state['target_hits'] = df
+        df['IKI_Netzero'] = df.apply(lambda x: 'T_NETZERO' if ((x['Netzero Label'] == 'NETZERO TARGET') & 
+                              (x['Conditional Label'] == 'UNCONDITIONAL'))
+                              else 'T_NETZERO_C' if ((x['Netzero Label'] == 'NETZERO TARGET') & 
+                              (x['Conditional Label'] == 'CONDITIONAL')
+                              )
+                              else None, axis=1
+                              )
+        def check_t(s,c):
+            temp = []
+            if (('Transport' in s) & (c== 'UNCONDITIONAL')):
+                temp.append('T_Transport_Unc')
+            if (('Transport' in s) & (c == 'CONDITIONAL')):
+                temp.append('T_Transport_C')
+            if (('Economy-wide' in s) & (c == 'CONDITIONAL')):
+                temp.append('T_Economy_C')
+            if (('Economy-wide' in s) & (c == 'UNCONDITIONAL')):
+                temp.append('T_Economy_Unc')
+            if (('Energy' in s) & (c == 'CONDITIONAL')):
+                temp.append('T_Energy_C')
+            if (('Energy' in s) & (c == 'UNCONDITIONAL')):
+                temp.append('T_Economy_Unc')
+            return temp
+        df['IKI_Target'] = df.apply(lambda x:check_t(x['Sector Label'], x['Conditional Label']),
+                                        axis=1 )
+
+        #  target_hits = st.session_state['target_hits']
+        df['keep'] = True
+
+
+        df = df[['text','IKI_Netzero','IKI_Target','Target Score','Netzero Label','GHG Label',
+            'Conditional Label','Sector Label','Adapt-Mitig Label','page','keep']]
+        st.dataframe(df)
+        # df = st.data_editor(
+        #           df,
+        #           column_config={
+        #               "keep": st.column_config.CheckboxColumn(
+        #                   help="Select which rows to keep",
+        #                   default=False,
+        #               )
+        #           },
+        #           disabled=list(set(df.columns) - {'keep'}),
+        #           hide_index=True,
+        #             )
+        # st.write("updating target hits....")
+        # st.write(len(df[df.keep == True]))
+        st.session_state['target_hits'] = df
+        
+    return
+
+
+# df = pd.read_csv(
+#     "https://raw.githubusercontent.com/mcnakhaee/palmerpenguins/master/palmerpenguins/data/penguins.csv"
+# )
+
+
+        # else:
+        #     st.info("🤔 No Targets found")
+            # count_df = df['Target Label'].value_counts()
+            # count_df = count_df.rename('count')
+            # count_df = count_df.rename_axis('Target Label').reset_index()
+            # count_df['Label_def'] = count_df['Target Label'].apply(lambda x: _lab_dict[x])
+                # st.plotly_chart(fig,use_container_width= True)
+            
+            # count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
+            # count_ghg = sum(hits['GHG Label'] == 'LABEL_2')
+            # count_economy = sum([True if 'Economy-wide' in x else False 
+            #                   for x in hits['Sector Label']])
+          # # excel part
+            # temp = df[df['Relevancy']>threshold]
+            
+            # df['Validation'] =  'No'
+            # df_xlsx = to_excel(df)
+            # st.download_button(label='📥 Download Current Result',
+            #                 data=df_xlsx ,
+            #                 file_name= 'file_target.xlsx')