Add application file

app.py

@@ -0,0 +1,128 @@
+import streamlit as st
+import pandas as pd
+import altair as alt
+
+# Streamlit app title
+st.title("Total Injuries and Fatalities by Month (Season)")
+
+# Load crash report data
+crash_data = pd.read_csv("1.08_Crash_Data_Report_(detail).csv")
+
+# Drop duplicate columns (X, Y are the same as Latitude and Longitude) -> from Janhavi's Part 1
+crash_data = crash_data.drop(['X', 'Y'], axis=1)
+
+# Drop rows with missing values in critical columns -> from Janhavi's Part 1
+crash_data.dropna(subset=['Incidentid', 'DateTime', 'Year', 'Latitude', 'Longitude'], inplace=True)
+
+# Filter rows where we have valid data for all necessary columns
+crash_data = crash_data[['DateTime', 'Totalinjuries', 'Totalfatalities', 'Unittype_One', 'Unittype_Two']].dropna()
+
+# Convert "DateTime" to datetime type
+crash_data['DateTime'] = pd.to_datetime(crash_data['DateTime'], errors='coerce')
+# crash_data['Month'] = crash_data['DateTime'].dt.month  # Incorrect extraction of month as numeric value, instead of name
+crash_data['Month'] = crash_data['DateTime'].dt.month_name()
+
+# sort months in order
+month_order = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December']
+crash_data['Month'] = pd.Categorical(crash_data['Month'], categories=month_order, ordered=True)
+
+# Dropdown for Unit Type selection
+# st.sidebar.selectbox("Select Unit Type", options=['Total'] + crash_data['Unittype_One'].dropna().unique().tolist())  # previous location of dropdown in sidebar
+# unit_type = st.selectbox("Select Unit Type", options=['Total'] + crash_data['Unittype_One'].dropna().unique().tolist())
+unit_type_pairs = set()
+for _, row in crash_data[['Unittype_One', 'Unittype_Two']].dropna().iterrows():
+    if row['Unittype_One'] != 'Driverless' or row['Unittype_Two'] != 'Driverless':
+        pair = ' vs '.join(sorted([row['Unittype_One'], row['Unittype_Two']]))
+        unit_type_pairs.add(pair)
+# unit_type_pairs = list(unit_type_pairs) # modified as below to sort the dropdown options in alphabetical order
+unit_type_pairs = sorted(list(unit_type_pairs))
+unit_type = st.selectbox("Select Unit Type Pair", options=['Total'] + unit_type_pairs)
+
+
+# Filter data based on the selected unit type
+if unit_type == 'Total':
+    filtered_data = crash_data
+else:
+    unit_one, unit_two = unit_type.split(' vs ')
+    filtered_data = crash_data[((crash_data['Unittype_One'] == unit_one) & (crash_data['Unittype_Two'] == unit_two)) |
+                               ((crash_data['Unittype_One'] == unit_two) & (crash_data['Unittype_Two'] == unit_one))]
+
+# Group data by month and calculate total injuries and fatalities
+monthly_sum = filtered_data.groupby('Month').agg({'Totalinjuries': 'sum', 'Totalfatalities': 'sum'}).reset_index()
+
+# Reshape the data for easier plotting
+injuries = monthly_sum[['Month', 'Totalinjuries']].rename(columns={'Totalinjuries': 'Value'})
+injuries['Measure'] = 'Total Injuries'
+
+fatalities = monthly_sum[['Month', 'Totalfatalities']].rename(columns={'Totalfatalities': 'Value'})
+fatalities['Measure'] = 'Total Fatalities'
+
+combined_data = pd.concat([injuries, fatalities])
+
+# Group data by month and calculate total injuries and fatalities
+monthly_sum = filtered_data.groupby('Month').agg({'Totalinjuries': 'sum', 'Totalfatalities': 'sum'}).reset_index()
+
+# Originally tried to use bar chart but switched to line chart for better trend visualization
+# alt.Chart(monthly_sum).mark_bar().encode(
+#     x=alt.X('Month', sort=month_order, title='Month'),
+#     y=alt.Y('Totalinjuries', title='Total Injuries', axis=alt.Axis(titleColor='blue', labelColor='blue', tickColor='blue')),
+#     color=alt.value('blue'),
+#     tooltip=['Month', 'Totalinjuries']
+# ).properties(
+#     title='Total Injuries and Fatalities by Month',
+#     width=300,
+#     height=300
+# ) + alt.Chart(monthly_sum).mark_bar().encode(
+#     x=alt.X('Month', sort=month_order, title='Month'),
+#     y=alt.Y('Totalfatalities', title='Total Fatalities', axis=alt.Axis(titleColor='red', labelColor='red', tickColor='red')),
+#     color=alt.value('red'),
+#     tooltip=['Month', 'Totalfatalities']
+# )
+
+# Plot line chart
+# line_chart = alt.Chart(monthly_sum).mark_line(point=True).encode(
+#     x=alt.X('Month', sort=month_order, title='Month'),
+#     y=alt.Y('Totalinjuries', title='Total Injuries & Fatalities', axis=alt.Axis(titleColor='black')),
+#     color=alt.value('blue'),
+#     tooltip=['Month', 'Totalinjuries']
+# ).properties(
+#     title=f'Total Injuries and Fatalities by Month for Unit Type Pair: {unit_type}',
+#     width=600,
+#     height=400
+# ) + alt.Chart(monthly_sum).mark_line(point=True).encode(
+#     x=alt.X('Month', sort=month_order, title='Month'),
+#     y=alt.Y('Totalfatalities', axis=alt.Axis(titleColor='red')),
+#     color=alt.value('red'),
+#     tooltip=['Month', 'Totalfatalities']
+# ).configure_legend(
+#     titleFontSize=14,
+#     labelFontSize=12,
+#     titleColor='black',
+#     labelColor='black'
+# )
+
+line_chart = alt.Chart(combined_data).mark_line(point=True).encode(
+    x=alt.X('Month:N', sort=month_order, title='Month'),
+    y=alt.Y('Value:Q', title='Total Injuries & Fatalities'),
+    color=alt.Color('Measure:N', title = '', scale=alt.Scale(domain=['Total Injuries', 'Total Fatalities'], range=['blue', 'red'])),
+    tooltip=['Month', 'Measure:N', 'Value:Q']
+).properties(
+    title=f'Total Injuries and Fatalities by Month for Unit Type Pair: {unit_type}',
+    width=600,
+    height=400
+)
+
+# # Combine the charts
+# combined_chart = alt.layer(line_chart_injuries, line_chart_fatalities).properties(
+#     title=f'Total Injuries and Fatalities by Month for Unit Type Pair: {unit_type}',
+#     width=600,
+#     height=400
+# ).configure_legend(
+#     titleFontSize=14,
+#     labelFontSize=12,
+#     titleColor='black',
+#     labelColor='black'
+# )
+
+# Display chart in Streamlit
+st.altair_chart(line_chart, use_container_width=True)