Started writing model implementation

src/model.py

@@ -0,0 +1,53 @@
+from darts import TimeSeries
+from darts.datasets import ILINetDataset
+from darts.metrics import mape
+from darts.model import ExponentialSmoothing
+from darts.utils.missing_values import fill_missing_values
+import numpy as np
+import pandas as pd
+
+def load_ILINetDataset():
+    """
+    Dataset's Components Descriptions:
+
+    * % WEIGHTED ILI: Combined state-specific data of patients visit to healthcare providers for ILI reported each week weighted by state population
+
+    * % UNWEIGHTED ILI: Combined state-specific data of patients visit to healthcare providers for ILI reported each week unweighted by state population
+
+    * AGE 0-4: Number of patients between 0 and 4 years of age
+
+    * AGE 25-49: Number of patients between 25 and 49 years of age
+
+    * AGE 25-64: Number of patients between 25 and 64 years of age
+
+    * AGE 5-24: Number of patients between 5 and 24 years of age
+
+    * AGE 50-64: Number of patients between 50 and 64 years of age
+
+    * AGE 65: Number of patients above (>=65) 65 years of age
+
+    * ILITOTAL: Total number of ILI patients. For this system, ILI is defined as fever (temperature of 100°F [37.8°C] or greater) and a cough and/or a sore throat
+
+    * NUM. OF PROVIDERS: Number of outpatient healthcare providers
+
+    * TOTAL PATIENTS: Total number of patients
+    """
+    ilidata = ILINetDataset().load().astype(np.float32)
+
+    return ilidata
+
+
+def preprocess_data(ilidata):
+    ilitotal = ilidata['ILITOTAL']
+    covariates = ilidata.drop_columns(col_names='ILITOTAL')
+
+    # Apply logaritmic transformation
+    log_ili = ilitotal.map(np.log)
+
+    # Remove -inf values
+    pd_log_ili = log_ili.pd_dataframe()
+    pd_log_ili['ILITOTAL'].replace(to_replace=-np.inf, value=np.nan, inplace=True)
+    log_ili = TimeSeries.from_dataframe(pd_log_ili)
+
+    log_ili = fill_missing_values(log_ili)
+