File size: 4,665 Bytes
359c749 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
import os
from datetime import date, datetime, timedelta
import joblib
import pandas as pd
import torch
from dotenv import load_dotenv
from huggingface_hub import hf_hub_download, login
from src.data_api_calls import (
get_combined_data,
update_pollution_data,
update_weather_data,
)
from src.features_pipeline import create_features
load_dotenv()
login(token=os.getenv("HUGGINGFACE_DOWNLOAD_TOKEN"))
def load_nn():
import torch.nn as nn
from huggingface_hub import PyTorchModelHubMixin
class AirPollutionNet(nn.Module, PyTorchModelHubMixin):
def __init__(self, input_size, layers, dropout_rate):
super(AirPollutionNet, self).__init__()
self.layers_list = nn.ModuleList()
in_features = input_size
for units in layers:
self.layers_list.append(nn.Linear(in_features, units))
self.layers_list.append(nn.ReLU())
self.layers_list.append(nn.Dropout(p=dropout_rate))
in_features = units
self.output = nn.Linear(in_features, 3) # Output size is 3 for next 3 days
def forward(self, x):
for layer in self.layers_list:
x = layer(x)
x = self.output(x)
return x
model = AirPollutionNet.from_pretrained(
"akseljoonas/Utrecht_pollution_forecasting_NO2"
)
return model
def load_model(particle):
repo_id = f"elisaklunder/Utrecht-{particle}-Forecasting-Model"
if particle == "O3":
file_name = "O3_svr_model.pkl"
model_path = hf_hub_download(repo_id=repo_id, filename=file_name)
model = joblib.load(model_path)
else:
model = load_nn()
return model
def run_model(particle, data):
input_data = create_features(data=data, target_particle=particle)
model = load_model(particle)
if particle == "NO2":
with torch.no_grad():
prediction = model(torch.tensor(input_data.values, dtype=torch.float32))
repo_id = "akseljoonas/Utrecht_pollution_forecasting_NO2"
file_name = "target_scaler_NO2.joblib"
path = hf_hub_download(repo_id=repo_id, filename=file_name)
else:
prediction = model.predict(input_data)
repo_id = f"elisaklunder/Utrecht-{particle}-Forecasting-Model"
file_name = f"target_scaler_{particle}.joblib"
path = hf_hub_download(repo_id=repo_id, filename=file_name)
target_scaler = joblib.load(path)
prediction = target_scaler.inverse_transform(prediction)
return prediction
def update_data_and_predictions():
update_weather_data()
update_pollution_data()
week_data = get_combined_data()
o3_predictions = run_model("O3", data=week_data)
no2_predictions = run_model("NO2", data=week_data)
prediction_data = []
for i in range(3):
prediction_data.append(
{
"pollutant": "O3",
"date_predicted": date.today(),
"date": date.today() + timedelta(days=i + 1),
"prediction_value": o3_predictions[0][i],
}
)
prediction_data.append(
{
"pollutant": "NO2",
"date_predicted": date.today(),
"date": date.today() + timedelta(days=i + 1),
"prediction_value": no2_predictions[0][i],
}
)
predictions_df = pd.DataFrame(prediction_data)
PREDICTIONS_FILE = "predictions_history.csv"
if os.path.exists(PREDICTIONS_FILE):
existing_data = pd.read_csv(PREDICTIONS_FILE)
# Filter out predictions made today to avoid duplicates
existing_data = existing_data[
~(existing_data["date_predicted"] == str(date.today()))
]
combined_data = pd.concat([existing_data, predictions_df])
combined_data.drop_duplicates()
else:
combined_data = predictions_df
combined_data.to_csv(PREDICTIONS_FILE, index=False)
def get_data_and_predictions():
week_data = get_combined_data()
PREDICTIONS_FILE = "predictions_history.csv"
data = pd.read_csv(PREDICTIONS_FILE)
today = datetime.today().strftime("%Y-%m-%d")
today_predictions = data[(data["date_predicted"] == today)]
# Extract predictions for O3 and NO2
o3_predictions = today_predictions[today_predictions["pollutant"] == "O3"][
"prediction_value"
].values
no2_predictions = today_predictions[today_predictions["pollutant"] == "NO2"][
"prediction_value"
].values
return week_data, [o3_predictions], [no2_predictions]
if __name__=="__main__":
update_data_and_predictions() |