Update app.py

app.py

@@ -74,8 +74,6 @@ def get_buses():
     short_bus_list = list(pd.unique(bus_df["route_short_name"]))
     return bus_df, bus_list, short_bus_list
 
-# Function to remove duplicates
-def remove_near_duplicates(data):
     print(data["trip_id"].nunique())
     result = []
     data["datetime"] = pd.to_datetime(data["datetime"])
@@ -97,75 +95,6 @@ def remove_near_duplicates(data):
     print(filtered_df["trip_id"].nunique())
     return filtered_df
 
-def remove_duplicate_trips(df, route_id_col="route_id", trip_id_col="trip_id", datetime_col="datetime", time_window='3min'):
-    """
-    Removes duplicate trips based on route_id and starting time proximity within a time window.
-    
-    Parameters:
-        df (pd.DataFrame): Input DataFrame containing trip data.
-        route_id_col (str): Column name for route IDs.
-        trip_id_col (str): Column name for trip IDs.
-        datetime_col (str): Column name for departure times.
-        time_window (str): Time window for considering trips as duplicates (e.g., '3min').
-    
-    Returns:
-        pd.DataFrame: Filtered DataFrame with duplicates removed.
-    """
-    print(df["trip_id"].nunique())
-
-    # Ensure the datetime column is of datetime type
-    df[datetime_col] = pd.to_datetime(df[datetime_col])
-
-    # Sort by route_id and datetime for correct chronological order within each route
-    df = df.sort_values(by=[route_id_col, datetime_col])
-
-    # Calculate time differences between consecutive rows within each route_id group
-    df['time_diff'] = df.groupby(route_id_col)[datetime_col].diff().fillna(pd.Timedelta('0s'))
-
-    # Mark rows as duplicates if the time difference is within the time window
-    time_window_timedelta = pd.to_timedelta(time_window)
-    df['is_duplicate'] = df['time_diff'] <= time_window_timedelta
-
-    # Keep only the first row within each group of duplicates (based on time window)
-    df['keep'] = ~df.groupby(route_id_col)['is_duplicate'].transform('any')
-
-    # Filter rows: Keep only those that are marked as 'keep'
-    result = df[df['keep']].drop(columns=['time_diff', 'is_duplicate', 'keep'])
-
-    print(result["trip_id"].nunique())
-    return result
-
-def plot_graph(plot_df):
-    #Nu vill vi plotta!
-    #TODO ska den bara visa de stopp man vill eller alla?
-    categories =  {0 : 'Empty',
-    1: 'Many seats available',
-    2:'Few seats available',
-    3:'Standing room only',
-    4:'Crushed standing room',
-    5: 'Full'}
-    
-    plot_df = plot_df[["datetime", "vehicle_occupancystatus", "stop_name", "route_id"]]
-    plot_df = plot_df.sort_values("datetime")
-    st.write(plot_df.head())
-    st.write(plot_df.tail())
-    #plot_df = plot_df.set_index("datetime")
-    plot_df["Occupancy"] = plot_df["vehicle_occupancystatus"].map(categories)
-    # Explicitly set the order for Y_category
-    category_order = list(categories.values())  # ['Empty', 'Many seats available', ..., 'Full']
-    category_order.reverse()
-
-    #st.line_chart(plot_df)
-    # Create the Altair chart
-    chart = alt.Chart(plot_df).mark_line(point=True, interpolate="step-after").encode(
-        x=alt.X('stop_name:N', title="Stop name"),  # Use column name as string
-        y=alt.Y('Occupancy:N', title="Vehicle Occupancy Status (Categories)", sort=category_order, scale=alt.Scale(domain=category_order)),  # Treat Y as categorical
-        tooltip=["datetime", 'stop_name', 'Occupancy']  # Add tooltips for interactivity
-    ).properties(
-        title="Vehicle Occupancy Status Over Time"
-    )
-    st.altair_chart(chart, use_container_width=True)
-
 def plot_graph_title(plot_df, stop, time):
     #Nu vill vi plotta!
     #TODO ska den bara visa de stopp man vill eller alla?
@@ -331,8 +260,6 @@ def drop_the_duplicates(df):
     return df
 
 
-
-
 # Streamlit UI
 def main():
     st.title("Wheely Fun Times - Bus Occupancy Explorer")