add exploration

exploration_app.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+import pickle
+import pandas as pd
+import streamlit as st
+from scipy import stats
+
+import plotly.express as px
+import plotly.figure_factory as ff
+
+import scipy
+import numpy as np
+from data_processing import load_data, process_data, get_monetary_dataframe, get_themes_per_year
+from model import prepare_predictors, prepare_data, run_training, split, predict, features_importance, run_cv_training, \
+    automl_training
+
+
+def _max_width_():
+    max_width_str = f"max-width: 1500px;"
+    st.markdown(
+        f"""
+    <style>
+    .reportview-container .main .block-container{{
+        {max_width_str}
+    }}
+    </style>    
+    """,
+        unsafe_allow_html=True,
+    )
+
+
+# force screen width
+_max_width_()
+
+st.title("Data Analysis 🌎 📃")
+st.write("by [Theolex](https://www.theolex.io/)")
+
+# load and process data
+data = load_data()
+decisions, organizations, authorities = process_data(data)
+
+col1, col2, col3, col4 = st.columns(4)
+
+with col1:
+    authorities_country = st.selectbox('Authority country', authorities.country.unique())
+
+with col2:
+    nb_years = st.selectbox('Number of years', range(1, 11), 4)
+
+with col3:
+    list_continents = decisions.org_continent.unique().tolist()
+    org_continent = st.selectbox("Company's continent", list_continents, list_continents.index("europe"))
+
+with col4:
+    list_company_types = decisions.org_company_type.unique().tolist()
+    org_company_type = st.selectbox("Company's activity", list_company_types,
+                                    list_company_types.index("Banking & Finance"))
+
+st.subheader(f"Which {authorities_country} regulators and prosecutors have been "
+             f"the most active in enforcement actions against {org_continent} "
+             f"{org_company_type} companies in the last {nb_years} years?")
+
+# apply filters
+select_auth = authorities[authorities.country == authorities_country].name.sort_values()
+authority_filter = decisions.authorities_name.apply(lambda a: bool(set(select_auth) & set(a)))
+year_filter = (decisions.year >= (2021 - nb_years))
+org_continent_filter = (decisions.org_continent == org_continent)
+org_company_type_filter = (decisions.org_company_type == org_company_type)
+decision_scope = decisions[authority_filter & year_filter & org_continent_filter & org_company_type_filter]
+
+decision_scope = decision_scope.explode("authorities_name")
+top_auths = decision_scope.groupby(['authorities_name'])['authorities_name'].count().sort_values(ascending=False).head(
+    5)
+
+fig = px.bar(top_auths,
+             template="simple_white",
+             color_continuous_scale='RdBu',
+             width=1200, height=600)
+st.plotly_chart(fig)
+
+with st.expander("Explore cases"):
+    st.dataframe(decision_scope[['authorities_name', 'org_name', 'decision_date', 'monetary_sanction', 'org_country',
+                                 'org_company_type']])
+
+# st.subheader("What are the top 10 negotiated settlements in France "
+#              "(involving French or foreign authorities) in the last 5 years?")
+#
+# st.subheader(
+#     "What are the top 3 areas (sanctions, anti-corruption, fraud, market manipulation, tax, etc.) "
+#     "of enforcement against banks in Germany in the last 3 years?")
+#
+# st.subheader("What are the largest enforcement actions involving French banks in the last 5 years?")
+#
+# st.subheader(
+#     "Which US regulators have imposed the largest penalties against financial institutions in the last 3 years?")

stream_app.py

@@ -61,6 +61,7 @@ st.subheader("Dataset Description")
 
 st.metric('Number of validated decisions linked to organisations (and not individuals)', decision_scope.shape[0])
 
+
 st.metric('Decisions with monetary sanctions',
           decision_scope[decision_scope.monetary_sanction > 0].shape[0])