admin/DATA11001-Introduction-to-Data-Science
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

---

Browse Source
This commit is contained in:
[Quy Anh] «Elliot» Nguyen
2026-06-24 16:52:08 +02:00
commit 5abeb4fd48
53 changed files with 276551 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/.dockerignore
+6
View File
@@ -0,0 +1,6 @@
env
datasets/20*
datasets/full_bike_data.csv
main.ipynb
deploy.sh
.env
backend/.env
View File
backend/Dockerfile
+14
View File
@@ -0,0 +1,14 @@
FROM python:3.13.0-bookworm
WORKDIR /usr/src/app
COPY . .
COPY .env.production .env
RUN pip install -r requirements.txt
EXPOSE 9000
ENV DJANGO_ENV=production
CMD ["python", "manage.py", "runserver", "0.0.0.0:9000", "--noreload"]
backend/README.md
+1
View File
@@ -0,0 +1 @@
## This is the Django backend for our Data Science project.
backend/app/__init__.py
View File
backend/app/admin.py
+3
View File
@@ -0,0 +1,3 @@
from django.contrib import admin
# Register your models here.
backend/app/apps.py
+6
View File
@@ -0,0 +1,6 @@
from django.apps import AppConfig
class AppConfig(AppConfig):
default_auto_field = 'django.db.models.BigAutoField'
name = 'app'
backend/app/migrations/__init__.py
View File
backend/app/models.py
+3
View File
@@ -0,0 +1,3 @@
from django.db import models
# Create your models here.
backend/app/tests.py
+3
View File
@@ -0,0 +1,3 @@
from django.test import TestCase
# Create your tests here.
backend/app/urls.py
+8
View File
@@ -0,0 +1,8 @@
from django.urls import path
from . import views
urlpatterns = [
path('', views.index, name='index'),
path('predict', views.predict, name='predict'),
]
backend/app/views.py
+80
View File
@@ -0,0 +1,80 @@
from django.http import HttpResponse, JsonResponse
from datetime import datetime
import pandas as pd
import statsmodels.api as sm
stations = ['Kamppi (M)', 'Rautatientori - itä']
station_dict = {}
for station in stations:
departure_data = pd.read_csv('datasets/' + station + '_hourly_aggregate.csv')
return_data = pd.read_csv('datasets/' + station + '_return_hourly_aggregate.csv')
departure_data['Departure'] = pd.to_datetime(departure_data['Departure'], format='mixed')
return_data['Return'] = pd.to_datetime(return_data['Return'], format='mixed')
departure_data.set_index(departure_data['Departure'], inplace=True)
return_data.set_index(return_data['Return'], inplace=True)
departure_data['trip'] = pd.to_numeric(departure_data['trip'], errors='coerce')
return_data['trip'] = pd.to_numeric(return_data['trip'], errors='coerce')
departure_data = departure_data.dropna(axis=1)
return_data = return_data.dropna(axis=1)
departure_mod = sm.tsa.statespace.SARIMAX(departure_data['trip'], order=(1, 1, 1), seasonal_order=(0, 1, 0, 24), freq='h').fit(disp=False, low_memory=True)
return_mod = sm.tsa.statespace.SARIMAX(return_data['trip'], order=(1, 1, 1), seasonal_order=(0, 1, 0, 24), freq='h').fit(disp=False, low_memory=True)
station_dict[station] = {}
station_dict[station]['departure_mod'] = departure_mod
station_dict[station]['return_mod'] = return_mod
def index(request):
return HttpResponse('You\'re at the app index.')
def predict(request):
if request.method == 'GET':
current = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
timestamp = request.GET.get('timestamp', current)
station = request.GET.get('station', 'Kamppi (M)')
ts = timestamp
defaultBikeCount = 28
departingCount = -1
if departure_data.index.max() >= pd.to_datetime(timestamp):
ls = departure_data[departure_data['Departure'] == ts]['trip'].tolist()
if len(ls) != 0:
departingCount = ls[0]
else:
pass
else:
departure_mod = station_dict[station]['departure_mod']
departForecast = departure_mod.forecast(timestamp)
departingCount = round(departForecast[-1])
returningCount = -1
if return_data.index.max() >= pd.to_datetime(timestamp):
ls = return_data[return_data['Return'] == ts]['trip'].tolist()
if len(ls) != 0:
returningCount = ls[0]
else:
pass
else:
return_mod = station_dict[station]['return_mod']
returnForecast = return_mod.forecast(timestamp)
returningCount = round(returnForecast[-1])
bikeAtStationCount = defaultBikeCount - departingCount + returningCount
result = {
'timestamp': timestamp,
'station': station,
'departingCount': departingCount,
'returningCount': returningCount,
'bikeAtStationCount': bikeAtStationCount,
'increasing': returningCount > departingCount
}
return JsonResponse(result)
backend/cross_validation_parameters.ipynb
+204
View File
@@ -0,0 +1,204 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "cd21c67a-e679-43e3-85a4-471a35522d42",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"\\nparam_mse = list()\\nfor param in parameter_space:\\n model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=param, seasonal_order=(0, 1, 0, 24), freq='h').fit()\\n forecast = model.forecast(datetime(year=2023,month=10,day=31,hour=17))\\n forecast = forecast[datetime(year=2023,month=4,day=1):]\\n #test_data.index = pd.DatetimeIndex(forecast.index)\\n \\n final = pd.concat([forecast,test_data], axis=1)\\n errors = final['trip'] - final['predicted_mean']\\n mse = np.mean(errors**2)\\n\\n param_mse.append((mse, param))\\n\""
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.model_selection import TimeSeriesSplit\n",
"from datetime import datetime\n",
"import statsmodels.api as sm\n",
"\n",
"# Use Kamppi as an example, could be generalized to all stations\n",
"df = pd.read_csv(\"datasets/Jämeräntaival_hourly_aggregate.csv\")\n",
"df['Departure'] = pd.to_datetime(df['Departure'], format='mixed')\n",
"df.set_index('Departure', inplace=True)\n",
"\n",
"train_end = datetime(year=2022, month=10, day=31)\n",
"train_start = datetime(year=2018,month=4,day=1)\n",
"train_data = df[:train_end]\n",
"test_end = datetime(year=2023, month=10, day = 31)\n",
"test_data = df[datetime(year=2023,month=4,day=1):]\n",
"\n",
"parameter_space = list()\n",
"\n",
"for i in range(0,3):\n",
" for j in range(0,3):\n",
" for k in range(0,3):\n",
" parameter_space.append((i,j,k))\n",
"\n",
"#parameter_space = [x for x in parameter_space if x[1] == 0]\n",
"parameter_space = [x for x in parameter_space if x != (0,0,0)]\n",
"'''\n",
"param_mse = list()\n",
"for param in parameter_space:\n",
" model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=param, seasonal_order=(0, 1, 0, 24), freq='h').fit()\n",
" forecast = model.forecast(datetime(year=2023,month=10,day=31,hour=17))\n",
" forecast = forecast[datetime(year=2023,month=4,day=1):]\n",
" #test_data.index = pd.DatetimeIndex(forecast.index)\n",
" \n",
" final = pd.concat([forecast,test_data], axis=1)\n",
" errors = final['trip'] - final['predicted_mean']\n",
" mse = np.mean(errors**2)\n",
"\n",
" param_mse.append((mse, param))\n",
"'''\n",
"\n",
"\n",
"\n",
" \n"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "db9591dd-7bfd-46d3-aa50-8a757776aeb0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"9.043665073451029 9.056463656418249\n",
"9.029642126494705 9.043665073451029\n",
"9.029317575211266 9.029642126494705\n",
"(np.float64(9.029317575211266), (1, 0, 2))\n"
]
}
],
"source": [
"min_mse = param_mse[0][0]\n",
"\n",
"index = 0\n",
"for i in range(0,len(param_mse)):\n",
" if param_mse[i][0] < min_mse:\n",
" print(param_mse[i][0], min_mse)\n",
" min_mse = param_mse[i][0]\n",
" index = i\n",
"\n",
"\n",
"print(param_mse[index])\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "5b01e8b2-19f2-4809-bee7-0e0589489841",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/aleksi/venv/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: No frequency information was provided, so inferred frequency h will be used.\n",
" self._init_dates(dates, freq)\n",
" This problem is unconstrained.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"RUNNING THE L-BFGS-B CODE\n",
"\n",
" * * *\n",
"\n",
"Machine precision = 2.220D-16\n",
" N = 3 M = 10\n",
"\n",
"At X0 0 variables are exactly at the bounds\n",
"\n",
"At iterate 0 f= 2.51523D+00 |proj g|= 8.46816D-02\n",
"\n",
"At iterate 5 f= 2.46808D+00 |proj g|= 9.28777D-03\n",
"\n",
"At iterate 10 f= 2.45763D+00 |proj g|= 8.55309D-03\n",
"\n",
"At iterate 15 f= 2.45509D+00 |proj g|= 5.19865D-03\n",
"\n",
"At iterate 20 f= 2.45471D+00 |proj g|= 1.64676D-03\n",
"\n",
"At iterate 25 f= 2.45467D+00 |proj g|= 4.36219D-04\n",
"\n",
"At iterate 30 f= 2.45467D+00 |proj g|= 2.78346D-06\n",
"\n",
" * * *\n",
"\n",
"Tit = total number of iterations\n",
"Tnf = total number of function evaluations\n",
"Tnint = total number of segments explored during Cauchy searches\n",
"Skip = number of BFGS updates skipped\n",
"Nact = number of active bounds at final generalized Cauchy point\n",
"Projg = norm of the final projected gradient\n",
"F = final function value\n",
"\n",
" * * *\n",
"\n",
" N Tit Tnf Tnint Skip Nact Projg F\n",
" 3 30 36 1 0 0 2.783D-06 2.455D+00\n",
" F = 2.4546707052577292 \n",
"\n",
"CONVERGENCE: NORM_OF_PROJECTED_GRADIENT_<=_PGTOL \n",
"10.388099588499935\n"
]
}
],
"source": [
"model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=(1,1,1), seasonal_order=(0,1,0,24), freq='h').fit()\n",
"forecast = model.forecast(datetime(year=2023,month=10,day=31,hour=17))\n",
"forecast = forecast[datetime(year=2023,month=4,day=1):]\n",
"#test_data.index = pd.DatetimeIndex(forecast.index)\n",
"\n",
"final = pd.concat([forecast,test_data], axis=1)\n",
"errors = final['trip'] - final['predicted_mean']\n",
"mse = np.mean(errors**2)\n",
"\n",
"print(mse)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "726acc6f-ea29-4bb6-8252-a6556ae10ac4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
backend/db.sqlite3
BIN
View File
Binary file not shown.
backend/error_metric_calculations_results.txt
+1
View File
@@ -0,0 +1 @@
[(np.float64(3.3274909833208963), 'no exogenous data'), (np.float64(3.158263780804383), 'just weather'), (np.float64(3.3220296790264277), 'just weekdays and hours'), (np.float64(3.1363872336562717), 'all exogenous')]
backend/forecast_error_metric_calculations.ipynb
+301
View File
@@ -0,0 +1,301 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 56,
"id": "cd21c67a-e679-43e3-85a4-471a35522d42",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"asd\n",
"asd2\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/otto/.pyenv/versions/3.11.2/lib/python3.11/site-packages/statsmodels/tsa/statespace/sarimax.py:966: UserWarning: Non-stationary starting autoregressive parameters found. Using zeros as starting parameters.\n",
" warn('Non-stationary starting autoregressive parameters'\n",
"/Users/otto/.pyenv/versions/3.11.2/lib/python3.11/site-packages/statsmodels/tsa/statespace/sarimax.py:978: UserWarning: Non-invertible starting MA parameters found. Using zeros as starting parameters.\n",
" warn('Non-invertible starting MA parameters found.'\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"RUNNING THE L-BFGS-B CODE\n",
"\n",
" * * *\n",
"\n",
"Machine precision = 2.220D-16\n",
" N = 8 M = 10\n",
"\n",
"At X0 0 variables are exactly at the bounds\n",
"\n",
"At iterate 0 f= 2.52687D+00 |proj g|= 3.92148D-01\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" This problem is unconstrained.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"At iterate 5 f= 2.24021D+00 |proj g|= 1.15085D-01\n",
"\n",
"At iterate 10 f= 2.19412D+00 |proj g|= 5.75993D-03\n",
"\n",
"At iterate 15 f= 2.19337D+00 |proj g|= 8.22902D-04\n",
"\n",
"At iterate 20 f= 2.19327D+00 |proj g|= 4.98625D-03\n",
"\n",
"At iterate 25 f= 2.19325D+00 |proj g|= 3.48694D-05\n",
"\n",
" * * *\n",
"\n",
"Tit = total number of iterations\n",
"Tnf = total number of function evaluations\n",
"Tnint = total number of segments explored during Cauchy searches\n",
"Skip = number of BFGS updates skipped\n",
"Nact = number of active bounds at final generalized Cauchy point\n",
"Projg = norm of the final projected gradient\n",
"F = final function value\n",
"\n",
" * * *\n",
"\n",
" N Tit Tnf Tnint Skip Nact Projg F\n",
" 8 25 26 1 0 0 3.487D-05 2.193D+00\n",
" F = 2.1932501470633761 \n",
"\n",
"CONVERGENCE: REL_REDUCTION_OF_F_<=_FACTR*EPSMCH \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/otto/.pyenv/versions/3.11.2/lib/python3.11/site-packages/statsmodels/tsa/statespace/sarimax.py:966: UserWarning: Non-stationary starting autoregressive parameters found. Using zeros as starting parameters.\n",
" warn('Non-stationary starting autoregressive parameters'\n",
"/Users/otto/.pyenv/versions/3.11.2/lib/python3.11/site-packages/statsmodels/tsa/statespace/sarimax.py:978: UserWarning: Non-invertible starting MA parameters found. Using zeros as starting parameters.\n",
" warn('Non-invertible starting MA parameters found.'\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"RUNNING THE L-BFGS-B CODE\n",
"\n",
" * * *\n",
"\n",
"Machine precision = 2.220D-16\n",
" N = 10 M = 10\n",
"\n",
"At X0 0 variables are exactly at the bounds\n",
"\n",
"At iterate 0 f= 2.52689D+00 |proj g|= 3.92567D-01\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" This problem is unconstrained.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"At iterate 5 f= 2.23987D+00 |proj g|= 1.15352D-01\n",
"\n",
"At iterate 10 f= 2.19343D+00 |proj g|= 5.82758D-03\n",
"\n",
"At iterate 15 f= 2.19242D+00 |proj g|= 1.41481D-03\n",
"\n",
"At iterate 20 f= 2.19228D+00 |proj g|= 1.02376D-03\n",
"\n",
"At iterate 25 f= 2.19225D+00 |proj g|= 8.93884D-04\n",
"\n",
"At iterate 30 f= 2.19224D+00 |proj g|= 6.02699D-05\n",
"\n",
"At iterate 35 f= 2.19224D+00 |proj g|= 4.09553D-04\n",
"\n",
"At iterate 40 f= 2.19223D+00 |proj g|= 4.81752D-04\n",
"\n",
"At iterate 45 f= 2.19220D+00 |proj g|= 9.39974D-04\n",
"\n",
"At iterate 50 f= 2.19205D+00 |proj g|= 5.16353D-03\n",
"\n",
" * * *\n",
"\n",
"Tit = total number of iterations\n",
"Tnf = total number of function evaluations\n",
"Tnint = total number of segments explored during Cauchy searches\n",
"Skip = number of BFGS updates skipped\n",
"Nact = number of active bounds at final generalized Cauchy point\n",
"Projg = norm of the final projected gradient\n",
"F = final function value\n",
"\n",
" * * *\n",
"\n",
" N Tit Tnf Tnint Skip Nact Projg F\n",
" 10 50 54 1 0 0 5.164D-03 2.192D+00\n",
" F = 2.1920465431369465 \n",
"\n",
"STOP: TOTAL NO. of ITERATIONS REACHED LIMIT \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/otto/.pyenv/versions/3.11.2/lib/python3.11/site-packages/statsmodels/base/model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
" warnings.warn(\"Maximum Likelihood optimization failed to \"\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.model_selection import TimeSeriesSplit\n",
"from datetime import datetime\n",
"import statsmodels.api as sm\n",
"\n",
"stations = ['Jämeräntaival']\n",
"data = pd.read_csv('datasets/' + stations[0] + '_hourly_aggregate.csv')\n",
"data['Departure'] = pd.to_datetime(data['Departure'], format='mixed')\n",
"\n",
"results = []\n",
"\n",
"weather_df = pd.read_csv('datasets/weather_hourly_helsinki.csv')\n",
"weather_df = weather_df.loc[1:, :]\n",
"weather_df.columns = weather_df.iloc[0]\n",
"weather_df = weather_df.loc[2:, :]\n",
"weather_df['time'] = pd.to_datetime(weather_df['time'], format='mixed')\n",
"\n",
"data = pd.merge(weather_df, data, how='inner', left_on='time', right_on='Departure')\n",
"data = data.drop(['time'], axis=1)\n",
"\n",
"data['temperature_2m (°C)'] = pd.to_numeric(data['temperature_2m (°C)'], errors='coerce')\n",
"data['rain (mm)'] = pd.to_numeric(data['rain (mm)'], errors='coerce')\n",
"data['trip'] = pd.to_numeric(data['trip'], errors='coerce')\n",
"\n",
"\n",
"# generation of weekday & hour series\n",
"datedata = pd.DataFrame()\n",
"datedata['date'] = data['Departure']\n",
"datedata['weekday'] = data['Departure'].dt.weekday\n",
"days = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat']\n",
"for day in days:\n",
" datedata[day] = 0\n",
" datedata.loc[datedata['date'].dt.weekday == 0, day] = 1\n",
"for i in range(0, 23):\n",
" asd = 'hour' + str(i)\n",
" days.append(asd)\n",
" datedata[asd] = 0\n",
" datedata.loc[datedata['date'].dt.hour == i, asd] = 1\n",
"\n",
"data = pd.merge(datedata, data, how='inner', left_on='date', right_on='Departure')\n",
"data.set_index(data['Departure'], inplace=True)\n",
"\n",
"\n",
"\n",
"train_end = datetime(year=2022, month=10, day=31)\n",
"train_start = datetime(year=2018,month=4,day=1)\n",
"train_data = data[:train_end]\n",
"test_end = datetime(year=2023, month=10, day = 31)\n",
"test_data = data[datetime(year=2023,month=4,day=1):]\n",
"\n",
"\n",
"def MASE(y_true, y_pred, y_train):\n",
" forecast = y_pred.reset_index(drop=True)\n",
" outsample = y_true[:].iloc[:len(y_pred)]\n",
" insample = y_train.reset_index(drop=True).to_numpy()\n",
" frequency=1\n",
" return np.mean(np.abs(forecast - outsample)) / np.mean(np.abs(insample[:-frequency] - insample[frequency:]))\n",
"\n",
"\n",
"# reset indexes as they do funky things\n",
"test_data.reset_index(drop=True, inplace=True)\n",
"train_data.reset_index(drop=True, inplace=True)\n",
"\n",
"print('')\n",
"\n",
"# no exogenous variables at all\n",
"model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=(3,1,2), seasonal_order=(1, 1, 1, 24)).fit()\n",
"forecast = model.forecast(steps=24*30*7)\n",
"forecast = forecast[:]\n",
"results.append((MASE(test_data['trip'], forecast, train_data['trip']), 'no exog'))\n",
"\n",
"#just the weather as exogenous data\n",
"exogenous = ['rain (mm)', 'temperature_2m (°C)']\n",
"model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=(3,1,2), seasonal_order=(1, 1, 1, 24), exog=train_data[exogenous]).fit()\n",
"forecast = model.forecast(steps=24*30*7, exog=test_data[exogenous].iloc[:(24*30*7)])\n",
"forecast = forecast[:]\n",
"results.append((MASE(test_data['trip'], forecast, train_data['trip']), 'just weather'))\n",
"\n",
"#just weekday + time of the day as exogenous\n",
"model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=(3,1,2), seasonal_order=(1, 1, 1, 24), exog=train_data[days]).fit()\n",
"forecast = model.forecast(steps=24*30*7, exog=test_data[days].iloc[:(24*30*7)])\n",
"forecast = forecast[:]\n",
"results.append((MASE(test_data['trip'], forecast, train_data['trip']), 'just timely stuff'))\n",
"\n",
"\n",
"#all exogenous variables\n",
"for asd in days:\n",
" exogenous.append(asd)\n",
"model = sm.tsa.statespace.SARIMAX(train_data['trip'], order=(3,1,2), seasonal_order=(1, 1, 1, 24), exog=train_data[exogenous]).fit()\n",
"forecast = model.forecast(steps=24*30*7, exog=test_data[exogenous].iloc[:(24*30*7)])\n",
"forecast = forecast[:]\n",
"results.append((MASE(test_data['trip'], forecast, train_data['trip']), 'all exogs'))\n",
"\n",
"\n",
"print(results)\n",
" \n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5b01e8b2-19f2-4809-bee7-0e0589489841",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
backend/initial_model.ipynb
+108
View File
@@ -0,0 +1,108 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 65,
"id": "edadd89f-0fc1-4e07-a249-2a0d4052258c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" SARIMAX Results \n",
"==============================================================================\n",
"Dep. Variable: Trip count No. Observations: 7999\n",
"Model: ARIMA(2, 1, 2) Log Likelihood -14325.727\n",
"Date: Thu, 26 Sep 2024 AIC 28661.454\n",
"Time: 17:35:05 BIC 28696.389\n",
"Sample: 04-01-2023 HQIC 28673.412\n",
" - 10-31-2023 \n",
"Covariance Type: opg \n",
"==============================================================================\n",
" coef std err z P>|z| [0.025 0.975]\n",
"------------------------------------------------------------------------------\n",
"ar.L1 0.4432 0.034 12.890 0.000 0.376 0.511\n",
"ar.L2 0.2343 0.009 26.703 0.000 0.217 0.251\n",
"ma.L1 -1.5914 0.035 -45.151 0.000 -1.660 -1.522\n",
"ma.L2 0.5926 0.035 16.913 0.000 0.524 0.661\n",
"sigma2 2.1040 0.015 136.783 0.000 2.074 2.134\n",
"===================================================================================\n",
"Ljung-Box (L1) (Q): 0.14 Jarque-Bera (JB): 29710.16\n",
"Prob(Q): 0.71 Prob(JB): 0.00\n",
"Heteroskedasticity (H): 0.77 Skew: 2.39\n",
"Prob(H) (two-sided): 0.00 Kurtosis: 11.15\n",
"===================================================================================\n",
"\n",
"Warnings:\n",
"[1] Covariance matrix calculated using the outer product of gradients (complex-step).\n",
"2024-02-28 07:00 0.438484\n",
"Freq: h, dtype: float64\n"
]
}
],
"source": [
"import pandas as pd\n",
"import statsmodels.api as sm\n",
"from statsmodels.tsa.arima.model import ARIMA\n",
"\n",
"import matplotlib.pyplot as plt\n",
"df = pd.read_csv('datasets/aggregated_2023_Designmuseo.csv')\n",
"df['Departure'] = pd.to_datetime(df['Departure'], format='mixed')\n",
"df['Trip count'] = pd.to_numeric(df['Trip count'])\n",
"\n",
"start_date = '2023-01-04 00:00'\n",
"end_date = '2023-31-10 23:00'\n",
"\n",
"start = pd.to_datetime(start_date, format = '%Y-%d-%m %H:%M')\n",
"end_date = pd.to_datetime(end_date, format = '%Y-%d-%m %H:%M')\n",
"dates = pd.DataFrame({'Departure':pd.date_range(start, end_date, freq='h')})\n",
"\n",
"\n",
"df3 = pd.concat([df, dates])\n",
"values = {'Trip count' : 0, 'Departure station id' : 7.0, 'Departure station name' : 'Designmuseo'}\n",
"df3.fillna(value=values, inplace = True)\n",
"df3 = df3.sort_values(by='Departure')\n",
"\n",
"df3.set_index('Departure', inplace=True)\n",
"df3.index = pd.DatetimeIndex(df3.index).to_period('h')\n",
"\n",
"model = ARIMA(df3['Trip count'], order=(2,1,2))\n",
"model_fit = model.fit()\n",
"# summary of fit model\n",
"print(model_fit.summary())\n",
"'''\n",
"print(df3.sort_values(by='Departure'))\n",
"plt.acorr(df3['Trip count'], maxlags = 1000)\n",
"plt.grid(True)\n",
"'''\n",
"'''\n",
"sm.graphics.tsa.plot_pacf(df3['Trip count'], lags =24, method='ywm')\n",
"plt.show()\n",
"'''\n",
"print(model_fit.forecast(1))\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
backend/main.ipynb
+1305
View File
File diff suppressed because one or more lines are too long
backend/manage.py
Executable
+22
View File
@@ -0,0 +1,22 @@
#!/usr/bin/env python
"""Django's command-line utility for administrative tasks."""
import os
import sys
def main():
"""Run administrative tasks."""
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'project.settings')
try:
from django.core.management import execute_from_command_line
except ImportError as exc:
raise ImportError(
"Couldn't import Django. Are you sure it's installed and "
"available on your PYTHONPATH environment variable? Did you "
"forget to activate a virtual environment?"
) from exc
execute_from_command_line(sys.argv)
if __name__ == '__main__':
main()
backend/project/__init__.py
View File
backend/project/asgi.py
+16
View File
@@ -0,0 +1,16 @@
"""
ASGI config for project project.
It exposes the ASGI callable as a module-level variable named ``application``.
For more information on this file, see
https://docs.djangoproject.com/en/5.1/howto/deployment/asgi/
"""
import os
from django.core.asgi import get_asgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'project.settings')
application = get_asgi_application()
backend/project/settings.py
+122
View File
@@ -0,0 +1,122 @@
"""
Django settings for project project.
Generated by 'django-admin startproject' using Django 5.1.1.
For more information on this file, see
https://docs.djangoproject.com/en/5.1/topics/settings/
For the full list of settings and their values, see
https://docs.djangoproject.com/en/5.1/ref/settings/
"""
from pathlib import Path
import os
from dotenv import load_dotenv
load_dotenv()
DJANGO_ENV = os.getenv('DJANGO_ENV', 'development')
__prod__ = DJANGO_ENV == 'production'
# Build paths inside the project like this: BASE_DIR / 'subdir'.
BASE_DIR = Path(__file__).resolve().parent.parent
# Quick-start development settings - unsuitable for production
# See https://docs.djangoproject.com/en/5.1/howto/deployment/checklist/
# SECURITY WARNING: keep the secret key used in production secret!
SECRET_KEY=os.getenv('SECRET_KEY') if __prod__ else 'django-insecure-tu6x-0wmq^rlhrlcd=k$p2ytx7jr7y0jp+*xhq8$(2g5(+ensv'
# SECURITY WARNING: don't run with debug turned on in production!
# DEBUG = False if __prod__ else True
DEBUG = True
# ALLOWED_HOSTS = [os.getenv('BACKEND_ORIGIN')] if __prod__ else ['.localhost', '127.0.0.1', '[::1]', '127.0.0.1:3000', 'localhost:3000']
ALLOWED_HOSTS = ['*']
# Application definition
INSTALLED_APPS = ['django.contrib.admin', 'django.contrib.auth', 'django.contrib.contenttypes', 'django.contrib.sessions', 'django.contrib.messages', 'django.contrib.staticfiles', 'corsheaders']
MIDDLEWARE = [
'django.middleware.security.SecurityMiddleware',
'django.contrib.sessions.middleware.SessionMiddleware',
'django.middleware.common.CommonMiddleware',
'django.middleware.csrf.CsrfViewMiddleware',
'django.contrib.auth.middleware.AuthenticationMiddleware',
'django.contrib.messages.middleware.MessageMiddleware',
'django.middleware.clickjacking.XFrameOptionsMiddleware',
'corsheaders.middleware.CorsMiddleware',
'django.middleware.common.CommonMiddleware',
]
ROOT_URLCONF = 'project.urls'
TEMPLATES = [
{
'BACKEND': 'django.template.backends.django.DjangoTemplates',
'DIRS': [],
'APP_DIRS': True,
'OPTIONS': {
'context_processors': [
'django.template.context_processors.debug',
'django.template.context_processors.request',
'django.contrib.auth.context_processors.auth',
'django.contrib.messages.context_processors.messages',
],
},
},
]
WSGI_APPLICATION = 'project.wsgi.application'
# Database
# https://docs.djangoproject.com/en/5.1/ref/settings/#databases
DATABASES = {
'default': {
'ENGINE': 'django.db.backends.sqlite3',
'NAME': BASE_DIR / 'db.sqlite3',
}
}
# Password validation
# https://docs.djangoproject.com/en/5.1/ref/settings/#auth-password-validators
AUTH_PASSWORD_VALIDATORS = [
{
'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
},
]
# Internationalization
# https://docs.djangoproject.com/en/5.1/topics/i18n/
LANGUAGE_CODE = 'en-us'
TIME_ZONE = 'UTC'
USE_I18N = True
USE_TZ = True
# Static files (CSS, JavaScript, Images)
# https://docs.djangoproject.com/en/5.1/howto/static-files/
STATIC_URL = 'static/'
# Default primary key field type
# https://docs.djangoproject.com/en/5.1/ref/settings/#default-auto-field
DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
CORS_ALLOW_ALL_ORIGINS = True
backend/project/urls.py
+23
View File
@@ -0,0 +1,23 @@
"""
URL configuration for project project.
The `urlpatterns` list routes URLs to views. For more information please see:
https://docs.djangoproject.com/en/5.1/topics/http/urls/
Examples:
Function views
1. Add an import: from my_app import views
2. Add a URL to urlpatterns: path('', views.home, name='home')
Class-based views
1. Add an import: from other_app.views import Home
2. Add a URL to urlpatterns: path('', Home.as_view(), name='home')
Including another URLconf
1. Import the include() function: from django.urls import include, path
2. Add a URL to urlpatterns: path('blog/', include('blog.urls'))
"""
from django.contrib import admin
from django.urls import include, path
urlpatterns = [
path('admin/', admin.site.urls),
path('app/', include('app.urls'))
]
backend/project/wsgi.py
+16
View File
@@ -0,0 +1,16 @@
"""
WSGI config for project project.
It exposes the WSGI callable as a module-level variable named ``application``.
For more information on this file, see
https://docs.djangoproject.com/en/5.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'project.settings')
application = get_wsgi_application()
backend/requirements.txt
+8
View File
@@ -0,0 +1,8 @@
pandas
numpy
matplotlib
seaborn
statsmodels
datetime
django-cors-headers
python-dotenv