Add Solar Alabama dataset

README.md

@@ -2,7 +2,7 @@
 
 <h3 align="center">Welcome to TSDB</h3>
 
-*<p align='center'>a Python toolbox to ease loading public time-series datasets</p>*
+*<p align='center'>a Python toolbox to ease loading 172 public time-series datasets</p>*
 
 <p align='center'>
     <a href='https://github.com/WenjieDu/TSDB'>
@@ -46,7 +46,7 @@
     </a>
 </p>
 
-> 📣 TSDB now supports a total of 1️⃣7️⃣0️⃣ time-series datasets ‼️
+> 📣 TSDB now supports a total of 1️⃣7️⃣2️⃣ time-series datasets ‼️
 
 <a href='https://github.com/WenjieDu/PyPOTS'><img src='https://pypots.com/figs/pypots_logos/PyPOTS/logo_FFBG.svg' width='160' align='left' /></a>
 TSDB is a part of
@@ -88,7 +88,9 @@ data = tsdb.load('physionet_2012')
 tsdb.download_and_extract('physionet_2012', './save_it_here')
 # datasets you once loaded are cached, and you can check them with list_cached_data()
 tsdb.list_cache()
-# you can delete only one specific dataset and preserve others
+# you can delete only one specific dataset's pickled cache
+tsdb.delete_cache(dataset_name='physionet_2012', only_pickle=True)
+# you can delete only one specific dataset raw files and preserve others
 tsdb.delete_cache(dataset_name='physionet_2012')
 # or you can delete all cache with delete_cached_data() to free disk space
 tsdb.delete_cache()
@@ -112,6 +114,8 @@ That's all. Simple and efficient. Enjoy it! 😃
 | [Electricity Load Diagrams](dataset_profiles/electricity_load_diagrams)                           | Forecasting, Imputation                 |
 | [Electricity Transformer Temperature (ETT)](dataset_profiles/electricity_transformer_temperature) | Forecasting, Imputation                 |
 | [Vessel AIS](dataset_profiles/vessel_ais)                                                         | Forecasting, Imputation, Classification |
+| [PeMS Traffic](dataset_profiles/pems_traffic)                                                     | Forecasting, Imputation                 |
+| [Solar Alabama](dataset_profiles/solar_alabama)                                                   | Forecasting, Imputation                 |
 | [UCR & UEA Datasets](dataset_profiles/ucr_uea_datasets) (all 163 datasets)                        | Classification                          |
 
 

dataset_profiles/solar_alabama/README.md

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

setup.py

@@ -8,7 +8,7 @@
 setup(
     name="tsdb",
     version=__version__,
-    description="TSDB (Time Series Data Beans): a Python toolbox helping load open-source time-series datasets",
+    description="TSDB (Time Series Data Beans): a Python toolbox helping load 172 open-source time-series datasets",
     long_description=README,
     long_description_content_type="text/markdown",
     license="BSD-3-Clause",

tests/test_tsdb.py

@@ -16,9 +16,12 @@
     "physionet_2012",
     "physionet_2019",
     "beijing_multisite_air_quality",
+    "italy_air_quality",
     "electricity_load_diagrams",
     "electricity_transformer_temperature",
     "vessel_ais",
+    "pems_traffic",
+    "solar_alabama",
     "ucr_uea_Wine",
 ]
 

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_alabama
+"""
+
+# 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