predictive app

app.py

@@ -8,6 +8,8 @@ from src.map_viz import calling_map_viz
 from src.data_ingestion import daily_average
 from src.heatmap import HeatMap
 from src.data_ingestion import remove_previous_view, merge_volumes
+from src.pred_plot import prep_data_pred_plot, data_split, train_model, predicted_figure, get_today, convert_date, gen_fig
+from datetime import date
 
 def fetch_data():
     # comment out for local testing, but be sure to include after testing
@@ -23,6 +25,7 @@ def fetch_data():
 
 def main():
     counts_df = fetch_data()
+    pred_df = counts_df.copy()
     counts_df = remove_previous_view(counts_df)
     counts_df = merge_volumes(counts_df)
     # st.set_page_config(layout="wide")
@@ -34,56 +37,80 @@ def main():
                 </style> """, 
                 unsafe_allow_html=True
                 )
-
+    hours = [
+        "00:00", "01:00", "02:00", "03:00", "04:00", "05:00",
+        "06:00", "07:00", "08:00", "09:00", "10:00", "11:00",
+        "12:00", "13:00", "14:00", "15:00", "16:00", "17:00",
+        "18:00", "19:00", "20:00", "21:00", "22:00", "23:00",
+    ]
     # Select Plot Option
-    st.sidebar.markdown("Select Plots to show")
-    checkbox_one = st.sidebar.checkbox('Overall Traffic', value = True) # rename as necessary
-    checkbox_two = st.sidebar.checkbox('Traffic Map', value = True)
-    checkbox_three = st.sidebar.checkbox('Heat Map', value = True)
-    view_options = list(counts_df["view"].unique())
-    view_options.append('All')
-    view = st.sidebar.selectbox("Choose View", options=view_options, index = view_options.index("Woodlands - to Johor"))
-    if view != 'All':
-        st.header(f"Showing Traffic for {view}")
-        counts_df = counts_df[counts_df['view'] == view]
+    plot_type = st.sidebar.selectbox("Choose Plot Type", options = ['Historical', 'Predictive'])
+    if plot_type == 'Historical':
+        st.sidebar.markdown("Select Plots to show")
+        checkbox_one = st.sidebar.checkbox('Overall Traffic', value = True) # rename as necessary
+        checkbox_two = st.sidebar.checkbox('Traffic Map', value = True)
+        checkbox_three = st.sidebar.checkbox('Heat Map', value = True)
+        view_options = list(counts_df["view"].unique())
+        view_options.append('All')
+        view = st.sidebar.selectbox("Choose View", options=view_options, index = view_options.index("Woodlands - to Johor"))
+        if view != 'All':
+            st.header(f"Showing Traffic for {view}")
+            counts_df = counts_df[counts_df['view'] == view]
+
+        if checkbox_one:
+            st.subheader("Overall Traffic")
+            plot = st.selectbox("Choose Plot", options=["Day", "Hour", "Raw"], index = 0)
+            st.plotly_chart(basic_chart(counts_df, plot = plot),use_container_width=True)
+
+        if checkbox_two:
+            st.subheader("Traffic Map")
+            st.pyplot(calling_map_viz(counts_df))
+        
+        if checkbox_three:
 
-    if checkbox_one:
-        st.subheader("Overall Traffic")
-        plot = st.selectbox("Choose Plot", options=["Day", "Hour", "Raw"], index = 0)
-        st.plotly_chart(basic_chart(counts_df, plot = plot),use_container_width=True)
+            heatmap = HeatMap(counts_df)
+            
+            # st.header("Mean Vehicle Count by Day of Week")
+            # st.plotly_chart(heatmap.vehicle_count_bar())
+            st.subheader("Heatmap")
+            st.plotly_chart(heatmap.heatmap())
 
-    if checkbox_two:
-        st.subheader("Traffic Map")
-        st.pyplot(calling_map_viz(counts_df))
-    
-    if checkbox_three:
+            hour_choice = st.selectbox(
+                "Choose Hour",
+                options= hours,
+                key = "hour", index = hours.index("08:00")
+            )
+            st.subheader(f"Traffic Volume of Each Day at {hour_choice}")
+            st.plotly_chart(heatmap.update_hour_bar_chart(hour_choice))
+            days = ["Monday", "Tuesday", "Wednesday", 
+                    "Thursday", "Friday","Saturday", "Sunday"]
+            day_choice = st.selectbox("Choose Day of the Week", options = days, key = "day", index = days.index("Saturday"))
+            st.subheader(f"Traffic Volume of Each Hour on {day_choice}")
+            st.plotly_chart(heatmap.update_day_bar_chart(day_choice))
 
-        heatmap = HeatMap(counts_df)
+    else: 
         
-        # st.header("Mean Vehicle Count by Day of Week")
-        # st.plotly_chart(heatmap.vehicle_count_bar())
-        st.subheader("Heatmap")
-        st.plotly_chart(heatmap.heatmap())
-        hours = [
-                "00:00", "01:00", "02:00", "03:00", "04:00", "05:00",
-                "06:00", "07:00", "08:00", "09:00", "10:00", "11:00",
-                "12:00", "13:00", "14:00", "15:00", "16:00", "17:00",
-                "18:00", "19:00", "20:00", "21:00", "22:00", "23:00",
-            ]
-        hour_choice = st.selectbox(
-            "Choose Hour",
+        figs = gen_fig()
+        today = get_today()
+        final_table = prep_data_pred_plot(pred_df)
+        x_train, _, y_train, _ = data_split(final_table)
+        clf = train_model(x_train, y_train)
+        pred_hour_choice = st.selectbox(
+            "Choose Your Planned Hour",
             options= hours,
-            key = "hour", index = hours.index("08:00")
+            key = "pred_hour", index = hours.index("08:00")
         )
-        
-        st.subheader(f"Traffic Volume of Each Day at {hour_choice}")
-        st.plotly_chart(heatmap.update_hour_bar_chart(hour_choice))
-        days = ["Monday", "Tuesday", "Wednesday", 
-                "Thursday", "Friday","Saturday", "Sunday"]
-        day_choice = st.selectbox("Choose Day of the Week", options = days, key = "day", index = days.index("Saturday"))
-        st.subheader(f"Traffic Volume of Each Hour on {day_choice}")
-        st.plotly_chart(heatmap.update_day_bar_chart(day_choice))
-        
+        pred_view_choice = st.selectbox(
+            "Choose View",
+            options= ['Johor-Tuas','Johor-Woodlands', 'Tuas-Johor', 'Woodlands-Johor'],
+            key = "pred_view"
+        )
+        d = st.date_input(
+            "Choose Your Planned Date",
+            date(today[0],today[1], today[2]))
+
+        starter_variables = [x_train, str(d), pred_hour_choice, pred_view_choice]
+        st.plotly_chart(predicted_figure(clf, starter_variables, figs))
 
 if __name__ == "__main__":
     main()

notebooks/pred_final.ipynb

@@ -0,0 +1,321 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using custom data configuration tappyness1--causion-f0c7d8cb97d796fc\n",
+      "Found cached dataset parquet (C:/Users/neoce/.cache/huggingface/datasets/tappyness1___parquet/tappyness1--causion-f0c7d8cb97d796fc/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)\n",
+      "100%|██████████| 1/1 [00:00<00:00, 144.77it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "import yaml\n",
+    "import sys\n",
+    "sys.path.append(\"..\")\n",
+    "from src.pred_plot import prep_data_pred_plot, data_split\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "token_file = open(\"../token_secret.yaml\")\n",
+    "token_obj = yaml.load(token_file, Loader=yaml.FullLoader)\n",
+    "dataset = load_dataset(\"tappyness1/causion\", use_auth_token=token_obj['TOKEN'])\n",
+    "counts_df = pd.DataFrame(dataset['train'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>time</th>\n",
+       "      <th>view</th>\n",
+       "      <th>car</th>\n",
+       "      <th>motorcycle</th>\n",
+       "      <th>large_vehicle</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2023-02-14</td>\n",
+       "      <td>22:36:03</td>\n",
+       "      <td>View_from_Second_Link_at_Tuas</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2023-02-14</td>\n",
+       "      <td>22:36:03</td>\n",
+       "      <td>View_from_Tuas_Checkpoint</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2023-02-14</td>\n",
+       "      <td>22:36:03</td>\n",
+       "      <td>View_from_Woodlands_Causeway_Towards_Johor</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2023-02-14</td>\n",
+       "      <td>22:36:03</td>\n",
+       "      <td>View_from_Woodlands_Checkpoint_Towards_BKE</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2023-02-14</td>\n",
+       "      <td>23:14:34</td>\n",
+       "      <td>View_from_Second_Link_at_Tuas</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         date      time                                        view  car  \\\n",
+       "0  2023-02-14  22:36:03               View_from_Second_Link_at_Tuas    0   \n",
+       "1  2023-02-14  22:36:03                   View_from_Tuas_Checkpoint    2   \n",
+       "2  2023-02-14  22:36:03  View_from_Woodlands_Causeway_Towards_Johor    2   \n",
+       "3  2023-02-14  22:36:03  View_from_Woodlands_Checkpoint_Towards_BKE    3   \n",
+       "4  2023-02-14  23:14:34               View_from_Second_Link_at_Tuas    0   \n",
+       "\n",
+       "   motorcycle  large_vehicle  \n",
+       "0           0              1  \n",
+       "1           0              0  \n",
+       "2           0              0  \n",
+       "3           0              1  \n",
+       "4           0              6  "
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "counts_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "g:\\My Drive\\DataScience\\OMSA GaTech\\08_CSE6242\\Project\\Org_Space\\Causion\\notebooks\\..\\src\\pred_plot.py:117: SettingWithCopyWarning:\n",
+      "\n",
+      "\n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "\n",
+      "g:\\My Drive\\DataScience\\OMSA GaTech\\08_CSE6242\\Project\\Org_Space\\Causion\\notebooks\\..\\src\\pred_plot.py:118: SettingWithCopyWarning:\n",
+      "\n",
+      "\n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "\n",
+      "g:\\My Drive\\DataScience\\OMSA GaTech\\08_CSE6242\\Project\\Org_Space\\Causion\\notebooks\\..\\src\\pred_plot.py:120: FutureWarning:\n",
+      "\n",
+      "The default value of numeric_only in DataFrameGroupBy.sum is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from src.pred_plot import prep_data_pred_plot, data_split, train_model, predicted_figure, get_today, convert_date, gen_fig\n",
+    "from datetime import date, datetime, timedelta\n",
+    "from jupyter_dash import JupyterDash\n",
+    "import dash\n",
+    "from dash import Dash, html, dcc, Input, Output\n",
+    "final_table = prep_data_pred_plot(counts_df)\n",
+    "x_train, x_test, y_train, y_test = data_split(final_table)\n",
+    "clf = train_model(x_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "starter_variables = [x_train, str(date.today()), \"07:00\", \"Tuas-Johor\"]\n",
+    "figs = gen_fig()\n",
+    "fig = predicted_figure(clf, starter_variables, figs)\n",
+    "today = get_today()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "app = JupyterDash(__name__)\n",
+    "\n",
+    "app.title = 'CSE6242 Dashboard'\n",
+    "app.layout = html.Div([\n",
+    "    html.Div([\n",
+    "    dcc.DatePickerSingle(\n",
+    "    id='my_date_picker_single',\n",
+    "        min_date_allowed=date(2023, 4, 11),\n",
+    "        max_date_allowed=date(2024, 4, 11),\n",
+    "        initial_visible_month=date(today[0],today[1], today[2]),\n",
+    "        date=date(today[0],today[1], today[2])\n",
+    "    ),\n",
+    "    html.Div(id='output-container-date-picker-single')],\n",
+    "        style={'width':'20%','height':'0px', 'padding-left':'2%',\n",
+    "                                                 'display':'inline-block'}),\n",
+    "    html.Div([dcc.Dropdown(id='hours_dropdown_id',\n",
+    "                                     options=['00:00', '01:00', '02:00', '03:00', '04:00', '05:00', '06:00', '07:00', '08:00', '09:00', \n",
+    "                         '10:00', '11:00', '12:00', '13:00', '14:00', '15:00', '16:00', '17:00', '18:00','19:00',\n",
+    "                         '20:00', '21:00', '22:00', '23:00'],\n",
+    "                                     value='07:00', clearable=False),html.Label(\"Estimated Leave Time\")],\n",
+    "    style={'width':'20%','height':'60px', 'padding-left':'2%',\n",
+    "                                                 'display':'inline-block'}),\n",
+    "    html.Div([dcc.Dropdown(id='direction_id',\n",
+    "                                     options=['Johor-Tuas','Johor-Woodlands',\n",
+    "                                             'Tuas-Johor', 'Woodlands-Johor'],\n",
+    "                                     value=\"Tuas-Johor\", clearable=False),html.Label(\"Direction\")],\n",
+    "    style={'width':'20%','height':'60px', 'padding-left':'2%',\n",
+    "                                                 'display':'inline-block'}),\n",
+    "    html.Div(dcc.Graph(id='final_output', figure=fig))])\n",
+    "\n",
+    "\n",
+    "@app.callback(Output('output-container-date-picker-single', 'children'),\n",
+    "    Input('my_date_picker_single', 'date'))\n",
+    "def update_output(date_value):\n",
+    "    string_prefix = 'Travel Day: '\n",
+    "    if date_value is not None:\n",
+    "        date_object = date.fromisoformat(date_value)\n",
+    "        date_string = convert_date(date_value)\n",
+    "        return string_prefix + date_string\n",
+    "    \n",
+    "@app.callback(Output('final_output', \"figure\"),\n",
+    "              Input('my_date_picker_single', 'date'),\n",
+    "              Input('hours_dropdown_id', 'value'),\n",
+    "              Input('direction_id', 'value'))\n",
+    "def update_final_output_hour(my_date_picker_single, hours_dropdown_id, direction_id):\n",
+    "    starter_variables[0] = x_train\n",
+    "    starter_variables[1] = str(my_date_picker_single)\n",
+    "    starter_variables[2] = str(hours_dropdown_id)\n",
+    "    starter_variables[3] = str(direction_id)\n",
+    "    fig = predicted_figure(clf, starter_variables, figs)\n",
+    "    return fig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dash is running on http://127.0.0.1:8050/\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "app.run_server(mode='inline')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2023-04-14'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from datetime import date\n",
+    "\n",
+    "str(date.today())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "causion",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.16"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/pred_plot.py

@@ -0,0 +1,203 @@
+from datetime import date, datetime, timedelta
+from sklearn.model_selection import train_test_split
+from sklearn.neural_network import MLPClassifier
+import pandas as pd
+import plotly.graph_objects as go
+
+def hour_rounder(t):
+    if int(t.minute)>= 30:
+        time_1 = str(int(t.hour)+1)
+        if len(time_1) == 1:
+            return "0"+time_1+":00"
+        else:
+            return str(time_1)+":00"
+    else:
+        if len(str(t.hour)) == 1:
+            return "0"+str(t.hour)+":00"
+        else:
+            return str(t.hour)+":00"
+        
+def peak_hours(t):
+    peak = ['07:00', "08:00", '09:00', "17:00", "18:00", "19:00"]
+    if t in peak:
+        return 1
+    else:
+        return 0
+    
+def weekend(w):
+    end = ['Saturday', 'Sunday']
+    if w in end:
+        return 1
+    else:
+        return 0
+    
+def vehicle_cat(v):
+    if v >= 0 and v < 20:
+        return 0
+    elif v >= 20 and v < 50:
+        return 1
+    elif v >= 50 and v < 80:
+        return 2
+    elif v >= 80 and v < 120:
+        return 3
+    else:
+        return 4 
+    
+def data_split(final_table):
+    X = final_table.loc[:,['day', 'hour','view']]
+    Y = final_table.loc[:,'cat']
+
+    X = pd.get_dummies(X)
+    X.loc[:,['peak', 'weekend']] = final_table.loc[:,['peak', 'weekend']]
+
+
+
+    x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.7,
+                                                                test_size=0.3,
+                                                                shuffle=True, random_state=13)
+    
+    return x_train, x_test, y_train, y_test 
+        
+def convert_date(date):
+    return datetime.strptime(date, "%Y-%m-%d").strftime('%A') 
+
+def create_row(x_train, date_d, hour, view):
+    if date_d is None:
+        date_d = "2023-04-11"
+    if hour is None:
+        hour = "09:00"
+    if view is None:
+        view = "Johor-Tuas"
+    
+    features = x_train.columns
+    d_dict = {}
+    day = datetime.strptime(date_d, "%Y-%m-%d").strftime('%A')
+    hour = str(hour)
+    view = str(view)
+    col_day = "day_" + day
+    col_hour = 'hour_'+ hour
+    col_view = 'view_'+view
+    
+    for i in features:
+        if i == col_day or i == col_hour or i == col_view:
+            d_dict[i] = [1]
+        else:
+            d_dict[i] = [0]
+    end = ['Saturday', 'Sunday']
+    peak = ['07:00', "08:00", '09:00', "17:00", "18:00", "19:00"]
+    
+    if day in end:
+        d_dict['weekend'] = 1
+    if hour in peak:
+        d_dict['peak'] = 1   
+    result = pd.DataFrame.from_dict(d_dict, orient='columns')
+    for i in features:
+        result[i] = result[i].astype('category')
+    return result
+
+def prep_data_pred_plot(df):
+    df = df.sort_values(by=['date']).reset_index(drop=True)
+    df['date'] = pd.to_datetime(df['date'], format = "%Y-%m-%d")
+    df['day'] = df['date'].dt.day_name()
+    df.drop(columns=['motorcycle'], axis=1, inplace=True)
+    df['vehicle'] = df['car'] + df['large_vehicle']
+
+    transfer = {"View_from_Second_Link_at_Tuas_to_sg": 'Johor-Tuas', 
+            "View_from_Second_Link_at_Tuas_to_jh": 'Tuas-Johor',
+            "View_from_Tuas_Checkpoint_to_sg": 'Johor-Tuas',
+            "View_from_Tuas_Checkpoint_to_jh": 'Tuas-Johor',
+            "View_from_Woodlands_Causeway_Towards_Johor_to_sg": 'Johor-Woodlands',
+            "View_from_Woodlands_Causeway_Towards_Johor_to_jh": 'Woodlands-Johor',
+            "View_from_Woodlands_Checkpoint_Towards_BKE_to_sg": 'Johor-Woodlands',
+            "View_from_Woodlands_Checkpoint_Towards_BKE_to_jh": 'Woodlands-Johor'}
+
+    new_table = df.replace({'view':transfer})
+    options = ['Johor-Woodlands','Woodlands-Johor','Johor-Tuas','Tuas-Johor']
+    final_df = new_table[new_table['view'].isin(options)]
+    final_df.loc[:, 'time'] = pd.to_datetime(final_df.loc[:,'time'], format='%H:%M:%S')
+    final_df.loc[:,'hour'] = final_df.loc[:,'time'].apply(hour_rounder)
+
+    final_table = final_df.groupby(['view', 'day', 'hour']).sum().reset_index().loc[:,['day', 'hour','view', 'vehicle']]
+
+    final_table.loc[:,'peak'] = final_table.loc[:,'hour'].apply(peak_hours)
+    final_table.loc[:,'peak'] = final_table.loc[:,'peak'].astype('category')
+    final_table.loc[:,'weekend'] = final_table.loc[:,'day'].apply(weekend)
+    final_table.loc[:,'weekend'] = final_table.loc[:,'weekend'].astype('category')
+    final_table.loc[:,'cat'] = final_table.loc[:,'vehicle'].apply(vehicle_cat)
+    final_table.loc[:,'cat'] = final_table.loc[:,'cat'].astype('category')
+
+    return final_table
+
+def gen_fig():
+    figs = []
+
+    for i in range(5):
+        midway = [15, 40, 70, 110, 150]
+        cat = ['No Traffic', 'Minimal Traffic', 'Mild Traffic', 'Moderate Traffic', 'Peak Traffic']
+        
+        figure = go.Figure(go.Indicator(
+                            mode = "gauge",
+                            value = midway[i],
+                            domain = {'x': [0, 1], 'y': [0, 1]},
+                            title = {'text': cat[i], 'font': {'size': 24}},
+                            gauge = {
+                                'axis': {'range': [None, 156], 'tickwidth': 1, 'tickcolor': "darkblue"},
+                                'bar': {'color': "blue"},
+                                'bgcolor': "white",
+                                'borderwidth': 2,
+                                'bordercolor': "gray",
+                                'steps': [
+                                    {'range': [0, 19], 'color': 'darkgreen'},
+                                    {'range': [20, 49], 'color': 'green'},
+                                    {'range': [50, 79], 'color': 'yellow'},
+                                    {'range': [80, 119], 'color': 'orange'},
+                                {'range': [120, 160], 'color': 'red'}],
+                                'threshold': {
+                                    'line': {'color': "red", 'width': 4},
+                                    'thickness': 0.75,
+                                    'value': 490}}))
+
+        figure.update_layout(paper_bgcolor = "lavender", font = {'color': "darkblue", 'family': "Arial"})
+
+        figs.append(figure)
+
+    return figs
+    
+def predicted_figure(clf, x, figs):
+    
+    result = create_row(x[0], x[1], x[2], x[3])
+
+    pred_val = clf.predict(result)[0]
+
+    return figs[pred_val]
+
+def get_today():
+    t = str(date.today()).split('-')
+    today = []
+
+    for i in t:
+        if t[0] =='0':
+            today.append(int(t[1:]))
+        else:
+            today.append(int(i))
+    return today
+
+def update_output(date_value):
+    string_prefix = 'Travel Day: '
+    if date_value is not None:
+        date_string = convert_date(date_value)
+        return string_prefix + date_string
+
+def update_final_output_hour(starter_variables, my_date_picker_single, hours_dropdown_id, direction_id):
+    # starter_variables = [clf, str(date.today()), "07:00", "Tuas-Johor"]
+    starter_variables[1] = str(my_date_picker_single)
+    starter_variables[2] = str(hours_dropdown_id)
+    starter_variables[3] = str(direction_id)
+    fig = predicted_figure(starter_variables)
+    return fig
+
+def train_model(x_train, y_train):
+    clf = MLPClassifier(solver='lbfgs', alpha=3, hidden_layer_sizes=(5,4), random_state=2, max_iter=3000)
+    clf.fit(x_train, y_train)
+
+    return clf