Spaces:
Sleeping
Sleeping
File size: 11,662 Bytes
a660599 1bc259c a660599 1bc259c 27403e9 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 30c2b16 c90b8f9 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 1bc259c a660599 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 |
import streamlit as st
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from Eda_functions import *
import numpy as np
import pickle
from streamlit_pandas_profiling import st_profile_report
import streamlit as st
import streamlit.components.v1 as components
import sweetviz as sv
from utilities import set_header,load_local_css
from st_aggrid import GridOptionsBuilder,GridUpdateMode
from st_aggrid import GridOptionsBuilder
from st_aggrid import AgGrid
import base64
import os
import tempfile
#from ydata_profiling import ProfileReport
import re
st.set_page_config(
page_title="Data Validation",
page_icon=":shark:",
layout="wide",
initial_sidebar_state='collapsed'
)
load_local_css('styles.css')
set_header()
with open('data_import.pkl', 'rb') as f:
data = pickle.load(f)
st.session_state['cleaned_data']= data['final_df']
st.session_state['category_dict'] = data['bin_dict']
st.title('Data Validation and Insights')
target_variables=[st.session_state['category_dict'][key] for key in st.session_state['category_dict'].keys() if key =='Response Metrics']
target_column = st.selectbox('Select the Target Feature/Dependent Variable (will be used in all charts as reference)',list(*target_variables))
st.session_state['target_column']=target_column
panels=st.session_state['category_dict']['Panel Level 1'][0]
selected_panels=st.multiselect('Please choose the panels you wish to analyze.If no panels are selected, insights will be derived from the overall data.',st.session_state['cleaned_data'][panels].unique())
aggregation_dict = {item: 'sum' if key == 'Media' else 'mean' for key, value in st.session_state['category_dict'].items() for item in value if item not in ['date','Panel_1']}
#st.write(st.session_state['cleaned_data'])
with st.expander('**Reponse Metric Analysis**'):
if len(selected_panels)>0:
st.session_state['Cleaned_data_panel']=st.session_state['cleaned_data'][st.session_state['cleaned_data']['Panel_1'].isin(selected_panels)]
st.session_state['Cleaned_data_panel']=st.session_state['Cleaned_data_panel'].groupby(by='date').agg(aggregation_dict)
st.session_state['Cleaned_data_panel']=st.session_state['Cleaned_data_panel'].reset_index()
else:
st.session_state['Cleaned_data_panel']=st.session_state['cleaned_data'].groupby(by='date').agg(aggregation_dict)
st.session_state['Cleaned_data_panel']=st.session_state['Cleaned_data_panel'].reset_index()
fig=line_plot_target(st.session_state['Cleaned_data_panel'], target=target_column, title=f'{target_column} Over Time')
st.plotly_chart(fig, use_container_width=True)
media_channel=list(*[st.session_state['category_dict'][key] for key in st.session_state['category_dict'].keys() if key =='Media'])
# st.write(media_channel)
Non_media_variables=list(*[st.session_state['category_dict'][key] for key in st.session_state['category_dict'].keys() if key =='Exogenous' or key=='Internal'])
st.markdown('### Annual Data Summary')
st.dataframe(summary(st.session_state['Cleaned_data_panel'], media_channel+[target_column], spends=None,Target=True), use_container_width=True)
if st.checkbox('Show raw data'):
st.write(pd.concat([pd.to_datetime(st.session_state['Cleaned_data_panel']['date']).dt.strftime('%m/%d/%Y'),st.session_state['Cleaned_data_panel'].select_dtypes(np.number).applymap(format_numbers)],axis=1))
col1 = st.columns(1)
if "selected_feature" not in st.session_state:
st.session_state['selected_feature']=None
def generate_report_with_target(channel_data, target_feature):
report = sv.analyze([channel_data, "Dataset"], target_feat=target_feature)
temp_dir = tempfile.mkdtemp()
report_path = os.path.join(temp_dir, "report.html")
report.show_html(filepath=report_path, open_browser=False) # Generate the report as an HTML file
return report_path
def generate_profile_report(df):
pr = df.profile_report()
temp_dir = tempfile.mkdtemp()
report_path = os.path.join(temp_dir, "report.html")
pr.to_file(report_path)
return report_path
#st.header()
with st.expander('Univariate and Bivariate Report'):
eda_columns=st.columns(2)
with eda_columns[0]:
if st.button('Generate Profile Report',help='Univariate report which inlcudes all statistical analysis'):
with st.spinner('Generating Report'):
report_file = generate_profile_report(st.session_state['Cleaned_data_panel'])
if os.path.exists(report_file):
with open(report_file, 'rb') as f:
st.success('Report Generated')
st.download_button(
label="Download EDA Report",
data=f.read(),
file_name="pandas_profiling_report.html",
mime="text/html"
)
else:
st.warning("Report generation failed. Unable to find the report file.")
with eda_columns[1]:
if st.button('Generate Sweetviz Report',help='Bivariate report for selected response metric'):
with st.spinner('Generating Report'):
report_file = generate_report_with_target(st.session_state['Cleaned_data_panel'], target_column)
if os.path.exists(report_file):
with open(report_file, 'rb') as f:
st.success('Report Generated')
st.download_button(
label="Download EDA Report",
data=f.read(),
file_name="report.html",
mime="text/html"
)
else:
st.warning("Report generation failed. Unable to find the report file.")
#st.warning('Work in Progress')
with st.expander('Media Variables Analysis'):
# Get the selected feature
st.session_state["selected_feature"]= st.selectbox('Select media', [col for col in media_channel if 'cost' not in col.lower() and 'spend' not in col.lower()])
# Filter spends features based on the selected feature
spends_features = [col for col in st.session_state['Cleaned_data_panel'].columns if any(keyword in col.lower() for keyword in ['cost', 'spend'])]
spends_feature = [col for col in spends_features if re.split(r'_cost|_spend', col.lower())[0] in st.session_state["selected_feature"]]
if 'validation' not in st.session_state:
st.session_state['validation']=[]
val_variables=[col for col in media_channel if col!='date']
if len(spends_feature)==0:
st.warning('No spends varaible available for the selected metric in data')
else:
fig_row1 = line_plot(st.session_state['Cleaned_data_panel'], x_col='date', y1_cols=[st.session_state["selected_feature"]], y2_cols=[target_column], title=f'Analysis of {st.session_state["selected_feature"]} and {[target_column][0]} Over Time')
st.plotly_chart(fig_row1, use_container_width=True)
st.markdown('### Summary')
st.dataframe(summary(st.session_state['cleaned_data'],[st.session_state["selected_feature"]],spends=spends_feature[0]),use_container_width=True)
cols2=st.columns(2)
with cols2[0]:
if st.button('Validate'):
st.session_state['validation'].append(st.session_state["selected_feature"])
with cols2[1]:
if st.checkbox('Validate all'):
st.session_state['validation'].extend(val_variables)
st.success('All media variables are validated ✅')
if len(set(st.session_state['validation']).intersection(val_variables))!=len(val_variables):
validation_data=pd.DataFrame({'Validate':[True if col in st.session_state['validation'] else False for col in val_variables],
'Variables':val_variables
})
cols3=st.columns([1,30])
with cols3[1]:
validation_df=st.data_editor(validation_data,
# column_config={
# 'Validate':st.column_config.CheckboxColumn(wi)
# },
column_config={
"Validate": st.column_config.CheckboxColumn(
default=False,
width=100,
),
'Variables':st.column_config.TextColumn(
width=1000
)
},hide_index=True)
selected_rows = validation_df[validation_df['Validate']==True]['Variables']
#st.write(selected_rows)
st.session_state['validation'].extend(selected_rows)
not_validated_variables = [col for col in val_variables if col not in st.session_state["validation"]]
if not_validated_variables:
not_validated_message = f'The following variables are not validated:\n{" , ".join(not_validated_variables)}'
st.warning(not_validated_message)
with st.expander('Non Media Variables Analysis'):
selected_columns_row4 = st.selectbox('Select Channel',Non_media_variables,index=1)
# # Create the dual-axis line plot
fig_row4 = line_plot(st.session_state['Cleaned_data_panel'], x_col='date', y1_cols=[selected_columns_row4], y2_cols=[target_column], title=f'Analysis of {selected_columns_row4} and {target_column} Over Time')
st.plotly_chart(fig_row4, use_container_width=True)
selected_non_media=selected_columns_row4
sum_df = st.session_state['Cleaned_data_panel'][['date', selected_non_media,target_column]]
sum_df['Year']=pd.to_datetime(st.session_state['Cleaned_data_panel']['date']).dt.year
#st.dataframe(df)
#st.dataframe(sum_df.head(2))
sum_df=sum_df.groupby('Year').agg('sum')
sum_df.loc['Grand Total']=sum_df.sum()
sum_df=sum_df.applymap(format_numbers)
sum_df.fillna('-',inplace=True)
sum_df=sum_df.replace({"0.0":'-','nan':'-'})
st.markdown('### Summary')
st.dataframe(sum_df,use_container_width=True)
with st.expander('Correlation Analysis'):
options = list(st.session_state['Cleaned_data_panel'].select_dtypes(np.number).columns)
# selected_options = []
# num_columns = 4
# num_rows = -(-len(options) // num_columns) # Ceiling division to calculate rows
# # Create a grid of checkboxes
# st.header('Select Features for Correlation Plot')
# tick=False
# if st.checkbox('Select all'):
# tick=True
# selected_options = []
# for row in range(num_rows):
# cols = st.columns(num_columns)
# for col in cols:
# if options:
# option = options.pop(0)
# selected = col.checkbox(option,value=tick)
# if selected:
# selected_options.append(option)
# # Display selected options
selected_options=st.multiselect('Select Variables For correlation plot',[var for var in options if var!= target_column],default=options[3])
st.pyplot(correlation_plot(st.session_state['Cleaned_data_panel'],selected_options,target_column))
|