Upload app.py

app.py

@@ -1,141 +1,140 @@
-import streamlit as st
-import pandas as pd
-import plotly.express as px
-from datetime import datetime
-
-excel_file_name = 'updated_dataset.csv'
-# Streamlit title
-st.title("Bangladesh Accident Monitoring System (BAMS)")
-
-
-# Display a note to the user
-st.write("Please Note, First Date must be smaller than Last date. Example: First Date = 25-08-2024 and Last Date = 28-08-2024")
-
-# Get today's date
-today = datetime.strptime(datetime.today().strftime('%d-%m-%Y'), '%d-%m-%Y')
-
-# Input fields for date range
-start = st.date_input("Enter first date", max_value=today, format="DD-MM-YYYY")
-start_string = start.strftime('%d-%m-%Y')
-end = st.date_input("Enter last date", max_value=today, format="DD-MM-YYYY")
-end_string = end.strftime('%d-%m-%Y')
-
-# Button to generate dataset based on date range
-if st.button("Generate Dataset"):
-    # Read the selected excel file
-    df3 = pd.read_csv(excel_file_name)
-
-    # Convert 'Publish Date' column to datetime with 'day-month-year' format
-    df3['Publish Date'] = pd.to_datetime(df3['Publish Date'], format='%d-%m-%Y')
-
-    # Convert user input dates to datetime
-    start_date = pd.to_datetime(start_string, format='%d-%m-%Y')
-    end_date = pd.to_datetime(end_string, format='%d-%m-%Y')
-
-    # Filter rows based on the specified date range
-    filtered_entries = df3[(df3['Publish Date'] >= start_date) & (df3['Publish Date'] <= end_date)]
-    filtered_entries.reset_index(inplace=True, drop=True)
-
-    # Display the filtered data
-    st.dataframe(filtered_entries)
-    
-    # Create a bar chart for accident count over days
-    if not filtered_entries.empty:
-        # Create a bar chart for accident count over days
-        if not filtered_entries.empty:
-            # Fixing date formats
-            for i in range(len(filtered_entries)):
-                if '/' in filtered_entries['Accident Date'][i]:
-                    day=int(filtered_entries['Accident Date'][i].split('/')[0])
-                    mon=int(filtered_entries['Accident Date'][i].split('/')[1])
-                    yr=int(filtered_entries['Acident Date'][i].split('/')[2])
-                    filtered_entries['Accident Date'][i]=f"{day}-{mon}-{yr}"
-            import pandas as pd
-            import plotly.express as px
-
-            # Convert 'Accident Date' to datetime format
-            filtered_entries['Accident Date'] = pd.to_datetime(filtered_entries['Accident Date'], format='%d-%m-%Y')
-
-            # Count accidents per date and sort by date
-            accident_counts = filtered_entries['Accident Date'].value_counts().sort_index()
-
-            # Reset the index and rename columns
-            accident_counts = accident_counts.reset_index()
-            accident_counts.columns = ['Accident Date', 'Accident Count']
-
-            # Convert 'Accident Date' back to string format
-            accident_counts['Accident Date'] = accident_counts['Accident Date'].dt.strftime('%d-%m-%Y')
-            filtered_entries['Accident Date'] = accident_counts['Accident Date']
-            fig1 = px.bar(accident_counts, 
-                        x='Accident Date', 
-                        y='Accident Count', 
-                        title="Accident Count Over Days",
-                        labels={'Accident Date': 'Date', 'Accident Count': 'Number of Accidents'},
-                        color='Accident Count',
-                        color_continuous_scale='Viridis')
-            st.plotly_chart(fig1)
-        # Convert 'Accident Date' to datetime format
-            filtered_entries['Accident Date'] = pd.to_datetime(filtered_entries['Accident Date'], format='%d-%m-%Y')
-
-            # Group by 'Accident Date' and sum the 'Killed' column
-            killed_per_day = filtered_entries.groupby('Accident Date')['Killed'].sum().reset_index()
-            killed_per_day.columns = ['Accident Date', 'Total Killed']
-
-            # Sort the dates in ascending order
-            killed_per_day = killed_per_day.sort_values(by='Accident Date')
-
-            # Convert 'Accident Date' back to string format
-            killed_per_day['Accident Date'] = killed_per_day['Accident Date'].dt.strftime('%d-%m-%Y')
-
-            fig2 = px.bar(killed_per_day, 
-                            x='Accident Date', 
-                            y='Total Killed', 
-                            title="Number of People Killed Each Day",
-                            labels={'Accident Date': 'Date', 'Total Killed': 'Number of People Killed'},
-                            color='Total Killed',
-                            color_continuous_scale='Reds')
-            st.plotly_chart(fig2)
-
-            # Bar chart showing the number of accidents in each district
-            district_accidents = filtered_entries['District'].value_counts().reset_index()
-            district_accidents.columns = ['District', 'Number of Accidents']
-            fig3 = px.bar(district_accidents, 
-                            x='District', 
-                            y='Number of Accidents',
-                            title="Accidents in Each District",
-                            labels={'Number of Accidents': 'Number of Accidents', 'District': 'District'},
-                            color='Number of Accidents',
-                            color_continuous_scale='Cividis')
-            st.plotly_chart(fig3)
-
-            ### Pie Chart Code ###
-            yes_count=0
-            no_count=0
-            not_available_count=0
-            for i in range(len(filtered_entries)):
-                if ('Yes' in filtered_entries['Pedestrian_Involved'][i] or 'yes' in filtered_entries['Pedestrian_Involved'][i]): yes_count+=1
-                if ('No' in filtered_entries['Pedestrian_Involved'][i] or 'no' in filtered_entries['Pedestrian_Involved'][i]): no_count+=1
-                if ('Not Available' in filtered_entries['Pedestrian_Involved'][i]): not_available_count+=1
-            Pedestrian_Involved_list = ['Yes', 'No', 'Not Available']
-            Count_list = [yes_count, no_count, not_available_count]
-            # dictionary of lists 
-            dict = {'Pedestrian Involved': Pedestrian_Involved_list, 'Count':Count_list} 
-            pedestrian_involvement = pd.DataFrame(dict)
-            # Pie chart showing the percentage of accidents involving pedestrians vs. those that don't
-            # pedestrian_involvement = filtered_entries['Pedestrian_Involved'].value_counts().reset_index()
-            # pedestrian_involvement.columns = ['Pedestrian Involved', 'Count']
-
-            fig4 = px.pie(pedestrian_involvement, 
-                            names='Pedestrian Involved', 
-                            values='Count', 
-                            title="Accidents Involving Pedestrians",
-                            labels={'Pedestrian Involved': 'Pedestrian Involved'},
-                            color_discrete_sequence=['Green', 'Red', 'Blue'])
-            st.plotly_chart(fig4)
-        
-    else:
-        st.write("No data available for the selected date range.")
-
-# Display selected start and end dates
-st.write("Start date is:", start)
-st.write("End date is:", end)
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+from datetime import datetime
+
+excel_file_name = 'updated_dataset.csv'
+# Streamlit title
+st.title("Bangladesh Accident Monitoring System (BAMS)")
+
+
+# Display a note to the user
+st.write("Please Note, First Date must be smaller than Last date. Example: First Date = 25-08-2024 and Last Date = 28-08-2024")
+
+# Get today's date
+today = datetime.strptime(datetime.today().strftime('%d-%m-%Y'), '%d-%m-%Y')
+
+# Input fields for date range
+start = st.date_input("Enter first date", max_value=today, format="DD-MM-YYYY")
+start_string = start.strftime('%d-%m-%Y')
+end = st.date_input("Enter last date", max_value=today, format="DD-MM-YYYY")
+end_string = end.strftime('%d-%m-%Y')
+
+# Button to generate dataset based on date range
+if st.button("Generate Dataset"):
+    # Read the selected excel file
+    df3 = pd.read_csv(excel_file_name)
+
+    # Convert 'Publish Date' column to datetime with 'day-month-year' format
+    df3['Publish Date'] = pd.to_datetime(df3['Publish Date'], format='%d-%m-%Y')
+
+    # Fixing date formats
+    for i in range(len(df3)):
+        if '/' in df3['Accident Date'][i]:
+            day=int(df3['Accident Date'][i].split('/')[0])
+            mon=int(df3['Accident Date'][i].split('/')[1])
+            yr=int(df3['Accident Date'][i].split('/')[2])
+            df3['Publish Date'][i]=f"{day}-{mon}-{yr}"
+    print(df3.tail())
+    # Convert user input dates to datetime
+    start_date = pd.to_datetime(start_string, format='%d-%m-%Y')
+    end_date = pd.to_datetime(end_string, format='%d-%m-%Y')
+
+    # Filter rows based on the specified date range
+    filtered_entries = df3[(df3['Publish Date'] >= start_date) & (df3['Publish Date'] <= end_date)]
+    filtered_entries.reset_index(inplace=True, drop=True)
+
+    # Display the filtered data
+    st.dataframe(filtered_entries)
+    # Create a bar chart for accident count over days
+    if not filtered_entries.empty:
+        # Create a bar chart for accident count over days
+        if not filtered_entries.empty:
+            import plotly.express as px
+
+            # Convert 'Accident Date' to datetime format
+            filtered_entries['Accident Date'] = pd.to_datetime(filtered_entries['Accident Date'], format='%d-%m-%Y')
+
+            # Count accidents per date and sort by date
+            accident_counts = filtered_entries['Accident Date'].value_counts().sort_index()
+
+            # Reset the index and rename columns
+            accident_counts = accident_counts.reset_index()
+            accident_counts.columns = ['Accident Date', 'Accident Count']
+
+            # Convert 'Accident Date' back to string format
+            accident_counts['Accident Date'] = accident_counts['Accident Date'].dt.strftime('%d-%m-%Y')
+            filtered_entries['Accident Date'] = accident_counts['Accident Date']
+            fig1 = px.bar(accident_counts, 
+                        x='Accident Date', 
+                        y='Accident Count', 
+                        title="Accident Count Over Days",
+                        labels={'Accident Date': 'Date', 'Accident Count': 'Number of Accidents'},
+                        color='Accident Count',
+                        color_continuous_scale='Viridis')
+            st.plotly_chart(fig1)
+        # Convert 'Accident Date' to datetime format
+            filtered_entries['Accident Date'] = pd.to_datetime(filtered_entries['Accident Date'], format='%d-%m-%Y')
+
+            # Group by 'Accident Date' and sum the 'Killed' column
+            killed_per_day = filtered_entries.groupby('Accident Date')['Killed'].sum().reset_index()
+            killed_per_day.columns = ['Accident Date', 'Total Killed']
+
+            # Sort the dates in ascending order
+            killed_per_day = killed_per_day.sort_values(by='Accident Date')
+
+            # Convert 'Accident Date' back to string format
+            killed_per_day['Accident Date'] = killed_per_day['Accident Date'].dt.strftime('%d-%m-%Y')
+
+            fig2 = px.bar(killed_per_day, 
+                            x='Accident Date', 
+                            y='Total Killed', 
+                            title="Number of People Killed Each Day",
+                            labels={'Accident Date': 'Date', 'Total Killed': 'Number of People Killed'},
+                            color='Total Killed',
+                            color_continuous_scale='Reds')
+            st.plotly_chart(fig2)
+
+            # Bar chart showing the number of accidents in each district
+            district_accidents = filtered_entries['District'].value_counts().reset_index()
+            district_accidents.columns = ['District', 'Number of Accidents']
+            fig3 = px.bar(district_accidents, 
+                            x='District', 
+                            y='Number of Accidents',
+                            title="Accidents in Each District",
+                            labels={'Number of Accidents': 'Number of Accidents', 'District': 'District'},
+                            color='Number of Accidents',
+                            color_continuous_scale='Cividis')
+            st.plotly_chart(fig3)
+
+            ### Pie Chart Code ###
+            yes_count=0
+            no_count=0
+            not_available_count=0
+            for i in range(len(filtered_entries)):
+                if ('Yes' in filtered_entries['Pedestrian_Involved'][i] or 'yes' in filtered_entries['Pedestrian_Involved'][i]): yes_count+=1
+                if ('No' in filtered_entries['Pedestrian_Involved'][i] or 'no' in filtered_entries['Pedestrian_Involved'][i]): no_count+=1
+                if ('Not Available' in filtered_entries['Pedestrian_Involved'][i]): not_available_count+=1
+            Pedestrian_Involved_list = ['Yes', 'No', 'Not Available']
+            Count_list = [yes_count, no_count, not_available_count]
+            # dictionary of lists 
+            dict = {'Pedestrian Involved': Pedestrian_Involved_list, 'Count':Count_list} 
+            pedestrian_involvement = pd.DataFrame(dict)
+            # Pie chart showing the percentage of accidents involving pedestrians vs. those that don't
+            # pedestrian_involvement = filtered_entries['Pedestrian_Involved'].value_counts().reset_index()
+            # pedestrian_involvement.columns = ['Pedestrian Involved', 'Count']
+
+            fig4 = px.pie(pedestrian_involvement, 
+                            names='Pedestrian Involved', 
+                            values='Count', 
+                            title="Accidents Involving Pedestrians",
+                            labels={'Pedestrian Involved': 'Pedestrian Involved'},
+                            color_discrete_sequence=['Green', 'Red', 'Blue'])
+            st.plotly_chart(fig4)
+        
+    else:
+        st.write("No data available for the selected date range.")
+
+# Display selected start and end dates
+st.write("Start date is:", start)
+st.write("End date is:", end)