style: parquet as optional package that the user has to install

MarkusPic · Nov 12, 2024 · 4da1308 · 4da1308
1 parent 65eeee6
commit 4da1308
Show file tree

Hide file tree

Showing 10 changed files with 18 additions and 9 deletions.
diff --git a/examples/convert_old_to_new_parameters.py b/examples/convert_old_to_new_parameters.py
@@ -9,6 +9,7 @@
 idf = IntensityDurationFrequencyAnalyse(series_kind=SERIES.PARTIAL, worksheet=METHOD.KOSTRA, extended_durations=True)
 
 # reading the pandas series of the precipitation (data from ehyd.gv.at - ID=112086)
+# You need to install `pyarrow` or `fastparquet` to read and write parquet files.
 # series = pd.read_parquet('ehyd_112086.parquet')['precipitation']
 
 # setting the series for the analysis

diff --git a/examples/example_60m.py b/examples/example_60m.py
@@ -8,6 +8,7 @@
 idf = IntensityDurationFrequencyAnalyse(series_kind=SERIES.PARTIAL, worksheet=METHOD.KOSTRA, extended_durations=True)
 
 # reading the pandas series of the precipitation (data from ehyd.gv.at - ID=112086)
+# You need to install `pyarrow` or `fastparquet` to read and write parquet files.
 series = pd.read_parquet('ehyd_112086.parquet')['precipitation']
 
 series60 = series.resample('60min').sum()

diff --git a/examples/example_heavy_rainfall_index.ipynb b/examples/example_heavy_rainfall_index.ipynb
@@ -28,7 +28,6 @@
     }
    },
    "source": [
-    "from os import path\n",
     "from pathlib import Path\n",
     "\n",
     "import matplotlib.pyplot as plt\n",
@@ -92,6 +91,11 @@
    "outputs": [],
    "execution_count": 3
   },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "You need to install `pyarrow` or `fastparquet` to read and write parquet files."
+  },
   {
    "cell_type": "code",
    "metadata": {
@@ -136,9 +140,7 @@
      "start_time": "2024-11-06T12:56:30.625338Z"
     }
    },
-   "source": [
-    "hri.auto_save_parameters(path.join(output_directory, 'idf_parameters.yaml'))"
-   ],
+   "source": "hri.auto_save_parameters(output_directory / 'idf_parameters.yaml')",
    "outputs": [],
    "execution_count": 7
   },

diff --git a/examples/example_python_api.ipynb b/examples/example_python_api.ipynb
@@ -103,7 +103,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "I used the rain-time-series from ehyd.gv.at with the ID 112086 (Graz-Andritz) [created with the ehyd-tools package](https://github.com/MarkusPic/ehyd_tools/blob/main/example/example_python_api.ipynb). "
+    "I used the rain-time-series from ehyd.gv.at with the ID 112086 (Graz-Andritz) [created with the ehyd-tools package](https://github.com/MarkusPic/ehyd_tools/blob/main/example/example_python_api.ipynb).\n",
+    "\n",
+    "You need to install `pyarrow` or `fastparquet` to read and write parquet files."
    ]
   },
   {

diff --git a/examples/example_python_api.py b/examples/example_python_api.py
@@ -13,6 +13,7 @@
 idf = HeavyRainfallIndexAnalyse(series_kind=SERIES.PARTIAL, worksheet=METHOD.KOSTRA, extended_durations=True)
 
 # reading the pandas series of the precipitation (data from ehyd.gv.at - ID=112086)
+# You need to install `pyarrow` or `fastparquet` to read and write parquet files.
 series = pd.read_parquet('ehyd_112086.parquet').squeeze()
 series.name = 'precipitation'
 

diff --git a/examples/example_python_api_extended.ipynb b/examples/example_python_api_extended.ipynb
@@ -68,6 +68,7 @@
     "idf = IntensityDurationFrequencyAnalyse(series_kind=SERIES.PARTIAL, worksheet=METHOD.KOSTRA, extended_durations=True)\n",
     "\n",
     "# reading the pandas series of the precipitation (data from ehyd.gv.at - ID=112086)\n",
+    "# You need to install `pyarrow` or `fastparquet` to read and write parquet files.\n",
     "series = pd.read_parquet('ehyd_112086.parquet').squeeze('columns') # ['precipitation']\n",
     "\n",
     "# setting the series for the analysis\n",

diff --git a/examples/example_python_api_extended.py b/examples/example_python_api_extended.py
@@ -11,6 +11,7 @@
 idf = IntensityDurationFrequencyAnalyse(series_kind=SERIES.PARTIAL, worksheet=METHOD.KOSTRA, extended_durations=True)
 
 # reading the pandas series of the precipitation (data from ehyd.gv.at - ID=112086)
+# You need to install `pyarrow` or `fastparquet` to read and write parquet files.
 series = pd.read_parquet('ehyd_112086.parquet')['N-Minutensummen-112086']
 
 # setting the series for the analysis

diff --git a/idf_analysis/in_out.py b/idf_analysis/in_out.py
@@ -33,6 +33,7 @@ def import_series(filename, series_label='precipitation', index_label='datetime'
 
         return ts
     elif filename.endswith('parquet'):
+        # You need to install `pyarrow` or `fastparquet` to read and write parquet files.
         return pd.read_parquet(filename, columns=[series_label])[series_label].rename_axis(index_label, axis='index')
     elif filename.endswith('pkl'):
         return pd.read_pickle(filename).rename(series_label).rename_axis(index_label, axis='index')

diff --git a/pyproject.toml b/pyproject.toml
@@ -29,7 +29,6 @@ dependencies = [
     "matplotlib",
     "scipy",
     "PyYAML>=5",
-    "pyarrow",
     "sympy"
 ]
 dynamic = ["version"]

diff --git a/requirements.txt b/requirements.txt
@@ -1,7 +1,7 @@
 pandas
 matplotlib
-tqdm>=4.67
+tqdm>=4.67  # optional
 scipy
 PyYAML>=5
-pyarrow
-sympy
+sympy
+# optional: You need to install `pyarrow` or `fastparquet` to read and write parquet files.