feat: add Python type hinting and annotations

Signed-off-by: Davide Madrisan <[email protected]>

hadcrut5_bars.py

@@ -6,13 +6,15 @@
 Display a bar plot of the HadCRUT5 Global temperature dataset.
 """
 
+import argparse
+
 import matplotlib.pyplot as plt
 import matplotlib.colors
 
 from hadcrut5lib import argparser, HadCRUT5
 
 
-def parse_args():
+def parse_args() -> argparse.Namespace:
     """This function parses and return arguments passed in"""
     descr = "Parse and plot the HadCRUT5 temperature datasets"
     examples = [
@@ -49,7 +51,8 @@ def parse_args():
     return parser.parse_args()
 
 
-def plotbar(period, outfile, verbose):
+# mypy: disable-error-code="misc, attr-defined"
+def plotbar(period: str, outfile: str, verbose: bool):
     """
     Create a bar plot for the specified period and diplay it or save it to file
     if outfile is set
@@ -81,7 +84,8 @@ def major_formatter(x, pos):
     plt.style.use("dark_background")
     _, ax = plt.subplots()
 
-    cmap = plt.cm.jet  # or plt.cm.bwr # pylint: disable=no-member
+    # pylint: disable=no-member
+    cmap = plt.cm.jet  # or plt.cm.bwr
     norm = matplotlib.colors.Normalize(vmin=-1, vmax=max(mean))
     colors = cmap(norm(mean))
 

hadcrut5_plot.py

@@ -6,7 +6,9 @@
 Display a plot of the HadCRUT5 temperature dataset.
 """
 
+import argparse
 from math import trunc
+from typing import List
 
 import matplotlib as mpl
 import matplotlib.pyplot as plt
@@ -15,7 +17,7 @@
 from hadcrut5lib import argparser, HadCRUT5
 
 
-def parse_args():
+def parse_args() -> argparse.Namespace:
     """This function parses and return arguments passed in"""
     descr = "Parse and plot the HadCRUT5 temperature datasets"
     examples = [
@@ -99,17 +101,17 @@ def parse_args():
     return parser.parse_args()
 
 
-def dataset_current_anomaly(temperatures):
+def dataset_current_anomaly(temperatures: List[float]) -> float:
     """Return the current anomaly"""
     return temperatures[-1]
 
 
-def dataset_max_anomaly(temperatures):
+def dataset_max_anomaly(temperatures: List[float]) -> float:
     """Return the maximum anomaly with respect to 'temperatures'"""
     return np.max(temperatures)
 
 
-def dataset_smoother(years, temperatures, chunksize):
+def dataset_smoother(years: List[int | float], temperatures: List[float], chunksize: int):
     """Make the lines smoother by using {chunksize}-year means"""
     data_range = range((len(years) + chunksize - 1) // chunksize)
     subset_years = [years[i * chunksize] for i in data_range]
@@ -120,7 +122,7 @@ def dataset_smoother(years, temperatures, chunksize):
     return subset_years, subset_temperatures
 
 
-def plotline(hc5, chunksize, annotate, outfile):
+def plotline(hc5: HadCRUT5, chunksize: int, annotate: int, outfile: str):
     """
     Create a plot for the specified period and arguments and diplay it or save
     it to file if outfile is set

hadcrut5_stripe.py

@@ -6,6 +6,9 @@
 Display a stripe image of the HadCRUT5 Global temperature dataset.
 """
 
+import argparse
+from typing import List
+
 import matplotlib.pyplot as plt
 from matplotlib.collections import PatchCollection
 from matplotlib.colors import ListedColormap
@@ -14,7 +17,7 @@
 from hadcrut5lib import argparser, HadCRUT5
 
 
-def parse_args():
+def parse_args() -> argparse.Namespace:
     """This function parses and return arguments passed in"""
     descr = "Parse and plot a stripe image of the HadCRUT5 temperature datasets"
     examples = [
@@ -59,7 +62,7 @@ def parse_args():
     return parser.parse_args()
 
 
-def plotstripe(region, outfile, labels, verbose):
+def plotstripe(region: str, outfile: str, labels: bool, verbose: bool):
     """
     Create a stripe plot for the specified period and diplay it or save it to
     file if outfile is set
@@ -74,7 +77,7 @@ def plotstripe(region, outfile, labels, verbose):
 
     years = hc5.dataset_years()
     yfirst, ylast = years[0], years[-1]
-    yrange = ylast - yfirst
+    yrange = int(ylast - yfirst)
 
     regions_switch = {
         "global": hc5.GLOBAL_REGION,
@@ -134,7 +137,7 @@ def plotstripe(region, outfile, labels, verbose):
         )
 
         ticks = [0, 0.2, 0.4, 0.6, 0.8, 1]
-        xlabels = [round(yfirst + x * yrange) for x in ticks]
+        xlabels: List[str] = [str(round(yfirst + x * yrange)) for x in ticks]
         plt.xticks(ticks, xlabels, fontweight="bold", fontsize=12)
     else:
         ax.get_xaxis().set_visible(False)

hadcrut5lib.py

@@ -11,6 +11,7 @@
 import json
 import logging
 import sys
+from typing import Dict, List, Mapping, Tuple
 
 import numpy as np
 import requests
@@ -28,15 +29,15 @@
 __status__ = "stable"
 
 
-def copyleft(descr):
+def copyleft(descr: str) -> str:
     """Print the Copyright message and License"""
     return (
         f"{descr} v{__version__} ({__status__})\n"
         "{__copyright__} <{__email__}>\nLicense: {__license__}"
     )
 
 
-def argparser(descr, examples):
+def argparser(descr: str, examples: List[str]) -> argparse.ArgumentParser:
     """Return a new ArgumentParser object"""
     return argparse.ArgumentParser(
         formatter_class=argparse.RawDescriptionHelpFormatter,
@@ -49,16 +50,16 @@ def argparser(descr, examples):
 class HadCRUT5:
     """Class for parsing and plotting HadCRUT5 datasets"""
 
-    # current dataset version
     _DATASET_VERSION = "5.0.2.0"
+    """current dataset version"""
 
-    # list of all the available data types
     _DEFAULT_DATATYPE = "annual"
     _VALID_DATATYPES = [_DEFAULT_DATATYPE, "monthly"]
+    """list of all the available data types"""
 
-    # list of all the valid periods
     _DEFAULT_PERIOD = "1961-1990"
     _VALID_PERIODS = [_DEFAULT_PERIOD, "1850-1900", "1880-1920"]
+    """list of all the valid periods"""
 
     GLOBAL_REGION = "Global"
     NORTHERN_REGION = "Northern Hemisphere"
@@ -114,10 +115,10 @@ def datasets_download(self):
         if self._enable_southern:
             self._wget_dataset_file(self._southern_hemisphere_filename)
 
-    def datasets_load(self):
+    def datasets_load(self) -> None:
         """Load all the netCDFv4 datasets"""
 
-        def dataset_load(dataset_filename):
+        def dataset_load(dataset_filename: str) -> Dict:
             """Load the data provided by the netCDFv4 file 'dataset_filename'"""
             dataset = nc_Dataset(dataset_filename)
             return {
@@ -126,7 +127,7 @@ def dataset_load(dataset_filename):
                 "variables": dataset.variables,
             }
 
-        def dataset_metadata_dump(dataset_name, dataset):
+        def dataset_metadata_dump(dataset_name: str, dataset) -> None:
             metadata = dataset["metadata"]
             self.logging_debug(
                 (f'Metadata for "{dataset_name}" dataset:\n{json.dumps(metadata, indent=2)}'),
@@ -145,14 +146,14 @@ def dataset_metadata_dump(dataset_name, dataset):
             self._datasets[region] = dataset_load(self._southern_hemisphere_filename)
             dataset_metadata_dump(region, self._datasets[region])
 
-    def datasets_normalize(self):
+    def datasets_normalize(self) -> None:
         """
         Normalize the temperature means to the required time period.
         Set _datasets_normalized with a tuple containing lower, mean, and upper
         temperatures for every enabled region
         """
 
-        def normalization_value(temperatures):
+        def normalization_value(temperatures: List[float]) -> float:
             """
             Return the value to be substracted to temperatures in order to
             obtain a mean-centered dataset for the required period
@@ -176,7 +177,7 @@ def normalization_value(temperatures):
                 raise ValueError(f'Unsupported period "{self._period}"')
 
             self.logging_debug("The mean anomaly in {self._period} is about {norm_temp:.8f}°C")
-            return norm_temp
+            return float(norm_temp)
 
         for region, data in self._datasets.items():
             mean = data["variables"]["tas_mean"]
@@ -196,26 +197,26 @@ def normalization_value(temperatures):
                 f"normalized dataset ({region}): mean \\\n{np.array(mean) - norm_temp}"
             )
 
-    def datasets_regions(self):
+    def datasets_regions(self) -> Mapping[str, object]:
         """Return the dataset regions set by the user at command-line"""
         return self._datasets.keys()
 
-    def logging(self, message):
+    def logging(self, message: str) -> None:
         """Print a message"""
         logging.info(message)
 
-    def logging_debug(self, message):
+    def logging_debug(self, message: str) -> None:
         """Print a message when in verbose mode only"""
         if self._verbose:
             logging.info(message)
 
-    def _hadcrut5_data_url(self, filename):
+    def _hadcrut5_data_url(self, filename: str) -> str:
         site = "https://www.metoffice.gov.uk"
         path = f"/hadobs/hadcrut5/data/HadCRUT.{self._DATASET_VERSION}/analysis/diagnostics/"
         url = f"{site}{path}{filename}"
         return url
 
-    def _wget_dataset_file(self, filename):
+    def _wget_dataset_file(self, filename: str) -> None:
         """Download a netCDFv4 HadCRUT5 file if not already found locally"""
         try:
             with open(filename, encoding="utf-8"):
@@ -240,31 +241,31 @@ def _wget_dataset_file(self, filename):
                     handle.write(block)
 
     @property
-    def dataset_datatype(self):
+    def dataset_datatype(self) -> str:
         """Return the datatype string"""
         return self._datatype
 
     @property
-    def dataset_history(self):
+    def dataset_history(self) -> str:
         """Return the datatype history from metadata"""
         # The datasets have all the same length so choose the first one
         region = list(self._datasets.keys())[0]
         metadata = self._datasets[region]["metadata"]
         return metadata.get("history")
 
-    def dataset_normalized_data(self, region):
+    def dataset_normalized_data(self, region) -> Tuple[List[float], List[float], List[float]]:
         """Return the dataset data normalized for the specified region"""
         lower = self._datasets_normalized[region]["lower"]
         mean = self._datasets_normalized[region]["mean"]
         upper = self._datasets_normalized[region]["upper"]
         return (lower, mean, upper)
 
     @property
-    def dataset_period(self):
+    def dataset_period(self) -> str:
         """Return the dataset period as a string"""
         return self._period
 
-    def dataset_years(self):
+    def dataset_years(self) -> List[int|float]:
         """
         Return an array of years corresponding of the loaded datasets.
         If the original dataset packages monthly data, the returning vector
@@ -279,7 +280,7 @@ def dataset_years(self):
         return years
 
     @property
-    def is_monthly_dataset(self):
+    def is_monthly_dataset(self) -> bool:
         """
         Return True if the loaded dataset provide monthly data,
         False otherwise