Update pages/market_rent_estimation.py

pages/market_rent_estimation.py

@@ -14,248 +14,249 @@ import geopandas as gpd
 def main():
     st.set_page_config(initial_sidebar_state="collapsed", layout="wide")
     tab1, tab2 = st.tabs(["Combined estimation", "Comps"])#, "Market distributions", "Rexy"])
+
+    distances_matrix = np.load('atlanta_matrix.npy')
+    df_properties = pd.read_csv("atlanta_data_new.csv", encoding='utf-8')
     
     
     with tab1:
-        st.title('Combined estimation')
-        if 'user_select_value' not in st.session_state:
-            st.session_state['user_select_value'] = ""
-        if 'year_buit' not in st.session_state:
-            st.session_state['year_buit'] = ""
-        if 'submarket_val' not in st.session_state:
-            st.session_state['submarket_val'] = ""
-        if 'market_val' not in st.session_state:
-            st.session_state['market_val'] = ""
+            st.write('Comps list:')
+            display_df = st.table(df_properties)
+    with tab2:
+            st.write('Comps list:')
+            st.write('min_property_size_perc:'st.session_state['min_property_size_perc'])
+            st.write('max_property_size_perc:'st.session_state['max_property_size_perc'])
+            st.write('months_back:'st.session_state['months_back'])
+    # with tab1:
+    #     st.title('Combined estimation')
+    #     if 'user_select_value' not in st.session_state:
+    #         st.session_state['user_select_value'] = ""
+    #     if 'year_buit' not in st.session_state:
+    #         st.session_state['year_buit'] = ""
+    #     if 'submarket_val' not in st.session_state:
+    #         st.session_state['submarket_val'] = ""
+    #     if 'market_val' not in st.session_state:
+    #         st.session_state['market_val'] = ""
 
-        box_contents = [
-            {"header": "Address", "content": st.session_state['user_select_value']},
-            {"header": "LSF", "content": str(st.session_state['property_lsf'])},
-            {"header": "Sub-Market", "content": st.session_state['submarket_val']},
-            {"header": "Market", "content": st.session_state['market_val']}
-        ]
+    #     box_contents = [
+    #         {"header": "Address", "content": st.session_state['user_select_value']},
+    #         {"header": "LSF", "content": str(st.session_state['property_lsf'])},
+    #         {"header": "Sub-Market", "content": st.session_state['submarket_val']},
+    #         {"header": "Market", "content": st.session_state['market_val']}
+    #     ]
 
-        # Divide the layout into four columns
-        col1, col2, col3, col4 = st.columns(4)
+    #     # Divide the layout into four columns
+    #     col1, col2, col3, col4 = st.columns(4)
         
-        for i, col in enumerate([col1, col2, col3, col4]):
-            col.markdown(f"""
-                <div style="padding: 20px; margin: 10px; text-align: center;">
-                    <h3 style="font-size: small;">{box_contents[i]['header']}</h3>
-                    <p style="font-size: small;">{box_contents[i]['content']}</p>
-                </div>
-            """, unsafe_allow_html=True)
+    #     for i, col in enumerate([col1, col2, col3, col4]):
+    #         col.markdown(f"""
+    #             <div style="padding: 20px; margin: 10px; text-align: center;">
+    #                 <h3 style="font-size: small;">{box_contents[i]['header']}</h3>
+    #                 <p style="font-size: small;">{box_contents[i]['content']}</p>
+    #             </div>
+    #         """, unsafe_allow_html=True)
             
-        # Add padding between the boxes and the slider
-        st.markdown('<style>div[data-testid="stBlock"]{margin-top: 20px;}</style>', unsafe_allow_html=True)
+    #     # Add padding between the boxes and the slider
+    #     st.markdown('<style>div[data-testid="stBlock"]{margin-top: 20px;}</style>', unsafe_allow_html=True)
         
-        def safe_eval(val):
-            try:
-                return ast.literal_eval(val)
-            except (ValueError, SyntaxError):
-                return val
+    #     def safe_eval(val):
+    #         try:
+    #             return ast.literal_eval(val)
+    #         except (ValueError, SyntaxError):
+    #             return val
                  
-        #comps results with scores
-        df_comps = pd.read_csv("comps_short_atlanta.csv")
-        # all properties
-        df_properties = pd.read_csv("atlanta_data.csv", encoding='utf-8')
+    #     #comps results with scores
+    #     df_comps = pd.read_csv("comps_short_atlanta.csv")
+    #     # all properties
+    #     df_properties = pd.read_csv("atlanta_data.csv", encoding='utf-8')
         
-        filtered_row = df_comps[df_comps['new_address'] == st.session_state['user_select_value']].iloc[0]
-        #addresses of comps
-        comps_addresses = filtered_row.filter(like='address_').tolist()
-        comps_addresses.insert(0, st.session_state['user_select_value'])
-        #similarity scores
-        comps_scores = filtered_row.filter(like='score_').tolist()
-        comps_scores.insert(0, 0)
+    #     filtered_row = df_comps[df_comps['new_address'] == st.session_state['user_select_value']].iloc[0]
+    #     #addresses of comps
+    #     comps_addresses = filtered_row.filter(like='address_').tolist()
+    #     comps_addresses.insert(0, st.session_state['user_select_value'])
+    #     #similarity scores
+    #     comps_scores = filtered_row.filter(like='score_').tolist()
+    #     comps_scores.insert(0, 0)
         
-        df_comps_data = df_properties[df_properties.google_ola.isin(comps_addresses)]
-        average_rent = df_comps_data.iloc[1:]['rent_combined'].mean()
+    #     df_comps_data = df_properties[df_properties.google_ola.isin(comps_addresses)]
+    #     average_rent = df_comps_data.iloc[1:]['rent_combined'].mean()
         
-        x1 ="Comps " + str(average_rent)
-        x3="Rexy " + str(st.session_state['prediction'])
+    #     x1 ="Comps " + str(average_rent)
+    #     x3="Rexy " + str(st.session_state['prediction'])
         
-        x2 = (st.session_state['prediction']+average_rent)/2
+    #     x2 = (st.session_state['prediction']+average_rent)/2
         
-        pick = st.select_slider(
-        "Combined estimation ",
-        options=[x1, x2, x3],
-        value=x2)
+    #     pick = st.select_slider(
+    #     "Combined estimation ",
+    #     options=[x1, x2, x3],
+    #     value=x2)
         
-        # st.markdown('<style>div[data-testid="stBlock"]{margin-top: 20px;}</style>', unsafe_allow_html=True)
+    #     # st.markdown('<style>div[data-testid="stBlock"]{margin-top: 20px;}</style>', unsafe_allow_html=True)
         
-        # st.markdown('<style>div[data-testid="stBlock"]{margin-top: 20px;}</style>', unsafe_allow_html=True)
+    #     # st.markdown('<style>div[data-testid="stBlock"]{margin-top: 20px;}</style>', unsafe_allow_html=True)
         
-        # chart_data = pd.DataFrame(np.random.randn(20, 2), columns=["col1", "col2"])
-        # chart_data['col4'] = np.random.choice(['A','B'], 20)
+    #     # chart_data = pd.DataFrame(np.random.randn(20, 2), columns=["col1", "col2"])
+    #     # chart_data['col4'] = np.random.choice(['A','B'], 20)
         
-        # st.scatter_chart(
-        #     chart_data,
-        #     x='col1',
-        #     y='col2',
-        #     color='col4',
-        # )
+    #     # st.scatter_chart(
+    #     #     chart_data,
+    #     #     x='col1',
+    #     #     y='col2',
+    #     #     color='col4',
+    #     # )
         
-        back_to_serach_tab1 = st.button("Search page")
-        if back_to_serach_tab1:
-            st.switch_page("app.py")
+    #     back_to_serach_tab1 = st.button("Search page")
+    #     if back_to_serach_tab1:
+    #         st.switch_page("app.py")
         
-    #comps page
-    with tab2:
-        # Create DataFrame
-        df_data = df_comps_data.copy().reset_index(drop=True)
+    # #comps page
+    # with tab2:
+    #     # Create DataFrame
+    #     df_data = df_comps_data.copy().reset_index(drop=True)
         
-        # filtered_data2 = df_dataF
-        filtered_data = df_data[["google_ola", "market_costar", "submarket_costar", "execution_date", "rented_sf", "building_sf", "year_built", "office_rate", "min_clear_height", "max_clear_height", "docks", "drive_ins", "rent_combined"]]#pd.concat([filtered_data2])
-        comps_scores = comps_scores[:len(filtered_data)]
-        filtered_data.insert(loc=1, column='Similarity score', value=comps_scores)
+    #     # filtered_data2 = df_dataF
+    #     filtered_data = df_data[["google_ola", "market_costar", "submarket_costar", "execution_date", "rented_sf", "building_sf", "year_built", "office_rate", "min_clear_height", "max_clear_height", "docks", "drive_ins", "rent_combined"]]#pd.concat([filtered_data2])
+    #     comps_scores = comps_scores[:len(filtered_data)]
+    #     filtered_data.insert(loc=1, column='Similarity score', value=comps_scores)
         
-        # Formatting the DataFrame 
-        filtered_data['Similarity score'] = ((1 - filtered_data['Similarity score']) * 100).apply(lambda x: f"{x:.2f}")
-        filtered_data['execution_date'] = pd.to_datetime(filtered_data['execution_date']).dt.strftime('%m-%d-%Y')
-        filtered_data['LSF (sf)'] = filtered_data['rented_sf'].round(0).astype(int)
-        filtered_data['RSF (sf)'] = filtered_data['building_sf'].round(0).astype(int)
-        filtered_data['Year built'] = filtered_data['year_built'].astype(int)
-        filtered_data.loc[filtered_data['office_rate'].notna(), 'office_rate'] = (filtered_data.loc[filtered_data['office_rate'].notna(), 'office_rate'] * 100).apply(lambda x: f"{x:.2f} %")
+    #     # Formatting the DataFrame 
+    #     filtered_data['Similarity score'] = ((1 - filtered_data['Similarity score']) * 100).apply(lambda x: f"{x:.2f}")
+    #     filtered_data['execution_date'] = pd.to_datetime(filtered_data['execution_date']).dt.strftime('%m-%d-%Y')
+    #     filtered_data['LSF (sf)'] = filtered_data['rented_sf'].round(0).astype(int)
+    #     filtered_data['RSF (sf)'] = filtered_data['building_sf'].round(0).astype(int)
+    #     filtered_data['Year built'] = filtered_data['year_built'].astype(int)
+    #     filtered_data.loc[filtered_data['office_rate'].notna(), 'office_rate'] = (filtered_data.loc[filtered_data['office_rate'].notna(), 'office_rate'] * 100).apply(lambda x: f"{x:.2f} %")
 
-        filtered_data.loc[filtered_data['min_clear_height'].notna(), 'min_clear_height'] = (filtered_data.loc[filtered_data['min_clear_height'].notna(), 'min_clear_height']).apply(lambda x: f"{int(x)}")
-        # filtered_data['Clear Height (feet)'] = filtered_data['min_clear_height'].round(0).astype(int)
+    #     filtered_data.loc[filtered_data['min_clear_height'].notna(), 'min_clear_height'] = (filtered_data.loc[filtered_data['min_clear_height'].notna(), 'min_clear_height']).apply(lambda x: f"{int(x)}")
+    #     # filtered_data['Clear Height (feet)'] = filtered_data['min_clear_height'].round(0).astype(int)
 
-        filtered_data.loc[filtered_data['docks'].notna(), 'docks'] = (filtered_data.loc[filtered_data['docks'].notna(), 'docks']).apply(lambda x: f"{int(x)}")
-        filtered_data.loc[filtered_data['drive_ins'].notna(), 'drive_ins'] = (filtered_data.loc[filtered_data['drive_ins'].notna(), 'drive_ins']).apply(lambda x: f"{int(x)}")
+    #     filtered_data.loc[filtered_data['docks'].notna(), 'docks'] = (filtered_data.loc[filtered_data['docks'].notna(), 'docks']).apply(lambda x: f"{int(x)}")
+    #     filtered_data.loc[filtered_data['drive_ins'].notna(), 'drive_ins'] = (filtered_data.loc[filtered_data['drive_ins'].notna(), 'drive_ins']).apply(lambda x: f"{int(x)}")
 
-        # filtered_data['Docks (/10ksf)'] = filtered_data['docks'].astype(int)
-        # filtered_data['Doors (/10ksf)'] = filtered_data['drive_ins'].astype(int)
-        filtered_data['Rent (NNN)'] = filtered_data['rent_combined'].apply(lambda x: f"${x:.2f}")
+    #     # filtered_data['Docks (/10ksf)'] = filtered_data['docks'].astype(int)
+    #     # filtered_data['Doors (/10ksf)'] = filtered_data['drive_ins'].astype(int)
+    #     filtered_data['Rent (NNN)'] = filtered_data['rent_combined'].apply(lambda x: f"${x:.2f}")
         
-        # Dropping old columns and renaming headers
-        filtered_data = filtered_data.drop(columns=['rented_sf', 'building_sf', 'year_built', 'max_clear_height', 'rent_combined'])
-        filtered_data = filtered_data.rename(columns={
-            'google_ola': 'Address',
-            'office_rate': 'Office %',
-            'min_clear_height': 'Clear Height (feet)',
-            'docks': 'Docks (/10ksf)',
-            'drive_ins': 'Doors (/10ksf)',
-            'market_costar': 'Market',
-            'submarket_costar': 'Submarket'
-        })
+    #     # Dropping old columns and renaming headers
+    #     filtered_data = filtered_data.drop(columns=['rented_sf', 'building_sf', 'year_built', 'max_clear_height', 'rent_combined'])
+    #     filtered_data = filtered_data.rename(columns={
+    #         'google_ola': 'Address',
+    #         'office_rate': 'Office %',
+    #         'min_clear_height': 'Clear Height (feet)',
+    #         'docks': 'Docks (/10ksf)',
+    #         'drive_ins': 'Doors (/10ksf)',
+    #         'market_costar': 'Market',
+    #         'submarket_costar': 'Submarket'
+    #     })
         
         
-        # Display the filtered data
-        col_1_1, col_1_2 = st.columns([2, 1])
-        with col_1_1:
-            st.write('Comps list:')
-            display_df = st.table(filtered_data)
-        with col_1_2:
-        # Create a map object
-            m = folium.Map(width=500, height=440, location=(df_data['lat'].mean(), df_data['long'].mean()), zoom_start=9)
+    #     # Display the filtered data
+    #     col_1_1, col_1_2 = st.columns([2, 1])
+    #     with col_1_1:
+    #         st.write('Comps list:')
+    #         display_df = st.table(filtered_data)
+    #     with col_1_2:
+    #     # Create a map object
+    #         m = folium.Map(width=500, height=440, location=(df_data['lat'].mean(), df_data['long'].mean()), zoom_start=9)
             
-            # Add markers to the map
-            all_markers = folium.FeatureGroup(name='All Markers')
-            active_markers = folium.FeatureGroup(name='Active Markers', show=False)
-            inactive_markers = folium.FeatureGroup(name='Inactive Markers', show=False)
+    #         # Add markers to the map
+    #         all_markers = folium.FeatureGroup(name='All Markers')
+    #         active_markers = folium.FeatureGroup(name='Active Markers', show=False)
+    #         inactive_markers = folium.FeatureGroup(name='Inactive Markers', show=False)
                 
-            for index, row in df_data.iterrows():
-                status_color = 'green' if index==0 else 'red'
-                html_content = f"""
-                <div style="
-                    display: inline-block;
-                    background-color: white;
-                    border: 2px solid black;
-                    border-radius: 50%;
-                    width: 20px;
-                    height: 20px;
-                    text-align: center;
-                    line-height: 20px;
-                    font-size: 8pt;
-                    color: {status_color};
-                ">{index}</div>
-                """
+    #         for index, row in df_data.iterrows():
+    #             status_color = 'green' if index==0 else 'red'
+    #             html_content = f"""
+    #             <div style="
+    #                 display: inline-block;
+    #                 background-color: white;
+    #                 border: 2px solid black;
+    #                 border-radius: 50%;
+    #                 width: 20px;
+    #                 height: 20px;
+    #                 text-align: center;
+    #                 line-height: 20px;
+    #                 font-size: 8pt;
+    #                 color: {status_color};
+    #             ">{index}</div>
+    #             """
                     
-                # Create a DivIcon with custom HTML content
-                icon = folium.DivIcon(html=html_content)
-                marker = folium.Marker([row['lat'], row['long']], popup=row['google_ola'], icon=icon).add_to(m)
+    #             # Create a DivIcon with custom HTML content
+    #             icon = folium.DivIcon(html=html_content)
+    #             marker = folium.Marker([row['lat'], row['long']], popup=row['google_ola'], icon=icon).add_to(m)
 
 
-            #add poligons on map
-            gdf = gpd.read_file('costar_sm_polygons.geojson')
-            gdf_Atlanta = gdf[gdf.full_submarket.str.contains("Atlanta")]
-            folium.GeoJson(data=gdf_Atlanta.geometry.to_json(), name='geojson').add_to(m)
-            for _, row in gdf_Atlanta.iterrows():
-                # Convert the row's geometry to GeoJSON
-                geojson = folium.GeoJson(data=row['geometry'].__geo_interface__,
-                                         style_function=lambda feature: {
-                                               'fillColor': '#00000000',  # Make the fill color transparent
-                                              'color': '#00000000',             # Set the border color
-                                               'weight': 2                  # Set the border width
-                                             },                                         
-                                        )
-                # Add a popup with the name
-                popup = folium.Popup(row['full_submarket'], parse_html=True)
+    #         #add poligons on map
+    #         gdf = gpd.read_file('costar_sm_polygons.geojson')
+    #         gdf_Atlanta = gdf[gdf.full_submarket.str.contains("Atlanta")]
+    #         folium.GeoJson(data=gdf_Atlanta.geometry.to_json(), name='geojson').add_to(m)
+    #         for _, row in gdf_Atlanta.iterrows():
+    #             # Convert the row's geometry to GeoJSON
+    #             geojson = folium.GeoJson(data=row['geometry'].__geo_interface__,
+    #                                      style_function=lambda feature: {
+    #                                            'fillColor': '#00000000',  # Make the fill color transparent
+    #                                            'color': '#00000000',             # Set the border color
+    #                                            'weight': 2                  # Set the border width
+    #                                          },                                         
+    #                                     )
+    #             # Add a popup with the name
+    #             popup = folium.Popup(row['full_submarket'], parse_html=True)
                 
-                # Add the GeoJson and Popup to the map
-                geojson.add_child(popup).add_to(m)
-    
-                # folium.GeoJson(
-                #     data=row['geometry'].__geo_interface__,
-                #     style_function=lambda feature: {
-                #         'fillColor': '#00000000',  # Make the fill color transparent
-                #         'color': 'blue',             # Set the border color
-                #         'weight': 2                  # Set the border width
-                #     },
-                #     tooltip=folium.Tooltip(row['full_submarket'])  # Add a tooltip with the name
-                # ).add_to(m)
+    #             # Add the GeoJson and Popup to the map
+    #             geojson.add_child(popup).add_to(m)
                     
-            # Add layer control to toggle marker visibility
-            folium.LayerControl().add_to(m)
+    #         # Add layer control to toggle marker visibility
+    #         folium.LayerControl().add_to(m)
             
-            # Render the map
-            folium_static(m)
+    #         # Render the map
+    #         folium_static(m)
             
-        option_add_comps = st.radio("Add comps:", (":rainbow[On]", ":rainbow[Off]"), horizontal=True, index=1)
-        if option_add_comps == ":rainbow[On]":
-            col_3_1, col_3_2, col_3_3 = st.columns([5,1,5])
-            with col_3_1:
-                # Create DataFrame
-                df5 = df_properties
-                df5.insert(loc=0, column='Select rows', value=[False]*len(df5))
-                st.write('Additional comps')
-                test = st.data_editor(
-                    df5,
-                    column_config={
-                        "Select rows": st.column_config.CheckboxColumn(
-                            "Your favorite?",
-                            help="Select your **favorite** widgets",
-                            default=False,
-                        )
-                    },
-                    # disabled=['Address','latitude','longitude','Match score','Market','Sub-market','Lease Date','LSF',
-                    # 'RSF','Rent (NNN)','Year Built','Office %','Clear Height','Doors (drive in / Dock)','Lease Term ','Rent (Gross)','TIs '],
-                    hide_index=True,
-                )
-            with col_3_2:
-                if st.button("Add comps", help="Click to add more comps"):
-                    filtered_data1 = pd.concat([filtered_data, test[test['Select rows']==True].drop(columns=['Select rows'])])
-                    # filtered_data.update(test.drop(columns=['favorite']))
-                    display_df.table(filtered_data1)
-            with col_3_3:
-                st.write('Filter definition')
+    #     option_add_comps = st.radio("Add comps:", (":rainbow[On]", ":rainbow[Off]"), horizontal=True, index=1)
+    #     if option_add_comps == ":rainbow[On]":
+    #         col_3_1, col_3_2, col_3_3 = st.columns([5,1,5])
+    #         with col_3_1:
+    #             # Create DataFrame
+    #             df5 = df_properties
+    #             df5.insert(loc=0, column='Select rows', value=[False]*len(df5))
+    #             st.write('Additional comps')
+    #             test = st.data_editor(
+    #                 df5,
+    #                 column_config={
+    #                     "Select rows": st.column_config.CheckboxColumn(
+    #                         "Your favorite?",
+    #                         help="Select your **favorite** widgets",
+    #                         default=False,
+    #                     )
+    #                 },
+    #                 # disabled=['Address','latitude','longitude','Match score','Market','Sub-market','Lease Date','LSF',
+    #                 # 'RSF','Rent (NNN)','Year Built','Office %','Clear Height','Doors (drive in / Dock)','Lease Term ','Rent (Gross)','TIs '],
+    #                 hide_index=True,
+    #             )
+    #         with col_3_2:
+    #             if st.button("Add comps", help="Click to add more comps"):
+    #                 filtered_data1 = pd.concat([filtered_data, test[test['Select rows']==True].drop(columns=['Select rows'])])
+    #                 # filtered_data.update(test.drop(columns=['favorite']))
+    #                 display_df.table(filtered_data1)
+    #         with col_3_3:
+    #             st.write('Filter definition')
                 
-                range_1 = st.slider('Lease date', min_value=0, max_value=36,
-                            value=(12))
-                range_2 = st.slider('Location in mi', min_value=0, max_value=50,
-                            value=(12))
-                range_3 = st.slider('LSF', min_value=0, max_value=500000, step = 1000,
-                            value=(20000, 200000))
-                range_4 = st.slider('Clear height', min_value=0, max_value=50,
-                            value=(15, 30))
-                range_5 = st.slider('Year built', min_value=1960, max_value=2024,
-                            value=(1999, 2010))
-                range_5 = st.slider('Far %', min_value=0, max_value=100,
-                            value=50)
-                range_6 = st.slider('Office %', min_value=0, max_value=100,
-                            value=30)
-                range_7 = st.slider('Docl doors & Drive-in', min_value=0, max_value=20,
-                            value=3)
-                st.button("Apply filter", key="submit_button", help="Click to submit")
+    #             range_1 = st.slider('Lease date', min_value=0, max_value=36,
+    #                         value=(12))
+    #             range_2 = st.slider('Location in mi', min_value=0, max_value=50,
+    #                         value=(12))
+    #             range_3 = st.slider('LSF', min_value=0, max_value=500000, step = 1000,
+    #                         value=(20000, 200000))
+    #             range_4 = st.slider('Clear height', min_value=0, max_value=50,
+    #                         value=(15, 30))
+    #             range_5 = st.slider('Year built', min_value=1960, max_value=2024,
+    #                         value=(1999, 2010))
+    #             range_5 = st.slider('Far %', min_value=0, max_value=100,
+    #                         value=50)
+    #             range_6 = st.slider('Office %', min_value=0, max_value=100,
+    #                         value=30)
+    #             range_7 = st.slider('Docl doors & Drive-in', min_value=0, max_value=20,
+    #                         value=3)
+    #             st.button("Apply filter", key="submit_button", help="Click to submit")
 
         back_to_serach_tab2 = st.button("Search page ")
         if back_to_serach_tab2: