feat: add Solar Alabama dataset;

dataset_profiles/solar_al/README.md

@@ -0,0 +1,5 @@
+# Solar Alabama
+
+## Citing this dataset 🤗
+
+`https://www.nrel.gov/grid/solar-power-data.html`

tsdb/data_processing.py

@@ -20,6 +20,7 @@
     load_ais,
     load_italy_air_quality,
     load_pems_traffic,
+    load_solar_alabama,
 )
 from .utils.downloading import download_and_extract
 from .utils.file import purge_path, pickle_load, pickle_dump, determine_data_home
@@ -108,6 +109,8 @@ def load(dataset_name: str, use_cache: bool = True) -> dict:
                 result = load_ais(dataset_saving_path)
             elif dataset_name == "pems_traffic":
                 result = load_pems_traffic(dataset_saving_path)
+            elif dataset_name == "solar_alabama":
+                result = load_solar_alabama(dataset_saving_path)
             elif "ucr_uea_" in dataset_name:
                 actual_dataset_name = dataset_name.replace(
                     "ucr_uea_", ""

tsdb/database.py

@@ -43,9 +43,12 @@
         "https://raw.githubusercontent.com/zhouhaoyi/ETDataset/main/ETT-small/ETTh1.csv",
         "https://raw.githubusercontent.com/zhouhaoyi/ETDataset/main/ETT-small/ETTh2.csv",
     ],
-    # https://pems.dot.ca.gov
+    # https://pems.dot.ca.gov, https://github.com/laiguokun/multivariate-time-series-data
     "pems_traffic": "https://raw.githubusercontent.com/laiguokun/multivariate-time-series-data/master/"
     "traffic/traffic.txt.gz",
+    # https://www.nrel.gov/grid/solar-power-data.html, https://github.com/laiguokun/multivariate-time-series-data
+    "solar_alabama": "https://raw.githubusercontent.com/laiguokun/multivariate-time-series-data/master/"
+    "solar-energy/solar_AL.txt.gz",
 }
 
 

tsdb/loading_funcs/__init__.py

@@ -14,6 +14,7 @@
 from .ucr_uea_datasets import load_ucr_uea_dataset
 from .vessel_ais import load_ais
 from .pems_traffic import load_pems_traffic
+from .solar_alabama import load_solar_alabama
 
 __all__ = [
     "load_beijing_air_quality",
@@ -25,4 +26,5 @@
     "load_ett",
     "load_italy_air_quality",
     "load_pems_traffic",
+    "load_solar_alabama",
 ]

tsdb/loading_funcs/solar_alabama.py

@@ -0,0 +1,50 @@
+"""
+Scripts related to dataset Solar Alabama. It contains the solar power production records in the year 2006,
+which are sampled every 10 minutes from 137 PV plants in Alabama State.
+https://www.nrel.gov/grid/solar-power-data.html
+
+For more information please refer to:
+https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/solar_al
+"""
+
+# Created by Wenjie Du <wenjay.du@gmail.com>
+# License: BSD-3-Clause
+
+import os
+
+import pandas as pd
+
+
+def load_solar_alabama(local_path):
+    """Load dataset Solar Alabama.
+
+    Parameters
+    ----------
+    local_path : str,
+        The local path of dir saving the raw data of Solar Alabama.
+
+    Returns
+    -------
+    data : dict
+        A dictionary contains X:
+            X : pandas.DataFrame
+                The time-series data of Solar Alabama.
+    """
+    dir_path = os.path.join(local_path, "solar_AL.txt")
+
+    # make columns names
+    col_names = [str(i) for i in range(137)]
+    df = pd.read_csv(dir_path, index_col=None, names=col_names)
+    date = pd.date_range(
+        start="2006-01-01 00:00:00",
+        end="2006-12-31 23:50:00",
+        freq="10min",
+    )
+    df["date"] = date
+    col_names.insert(0, "date")
+    df = df[col_names]
+
+    data = {
+        "X": df,
+    }
+    return data