Merge pull request #14 from oceanmodeling/fixes

fixes

Author: tomsail

.github/workflows/run_tests.yml

@@ -37,11 +37,11 @@ jobs:
         shell: "bash -eo pipefail {0}"
 
     steps:
-      - uses: "actions/checkout@v2"
-      - uses: "actions/setup-python@v2"
+      - uses: "actions/checkout@v3"
+      - uses: "actions/setup-python@v3"
         with:
           python-version: "${{ matrix.python }}"
-      - uses: "actions/cache@v2"
+      - uses: "actions/cache@v3"
         id: "cache"
         with:
           path: "${{ env.pythonLocation }}"

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ fail_fast: false
 
 repos:
   - repo: "https://github.com/pre-commit/pre-commit-hooks"
-    rev: "v4.5.0"
+    rev: "v5.0.0"
     hooks:
       - id: "check-added-large-files"
         args: ["--maxkb=40000"]
@@ -34,21 +34,21 @@ repos:
       - id: "python-use-type-annotations"
 
   - repo: "https://github.com/asottile/reorder_python_imports"
-    rev: "v3.12.0"
+    rev: "v3.14.0"
     hooks:
       - id: "reorder-python-imports"
         args:
           - "--py38-plus"
 
   - repo: "https://github.com/astral-sh/ruff-pre-commit"
     # Ruff version.
-    rev: "v0.1.7"
+    rev: "v0.11.7"
     hooks:
       - id: "ruff"
       - id: "ruff-format"
 
   - repo: "https://github.com/kynan/nbstripout"
-    rev: "0.6.1"
+    rev: "0.8.1"
     hooks:
       - id: "nbstripout"
 
@@ -63,33 +63,11 @@ repos:
       - id: "poetry-lock"
         name: "poetry lock --no-update"
         args: ["--no-update"]
-      - id: "poetry-export"
-        name: "poetry export main"
-        args:
-          [
-            "--only",
-            "main",
-            "-f",
-            "requirements.txt",
-            "-o",
-            "requirements/requirements.txt",
-          ]
-      - id: "poetry-export"
-        name: "poetry export dev"
-        args:
-          [
-            "--with",
-            "dev",
-            "-f",
-            "requirements.txt",
-            "-o",
-            "requirements/requirements-dev.txt",
-          ]
-
-  - repo: "local"
-    hooks:
-      - id: "mypy"
-        name: "mypy"
-        entry: "make mypy"
-        language: "system"
-        types: ["python"]
+      - id: poetry-export
+        args: ["-f", "requirements.txt", "-o", "requirements/requirements.txt"]
+        verbose: true
+        pass_filenames: false
+      - id: poetry-export
+        args: ["--dev", "-f", "requirements.txt", "-o", "requirements/requirements-dev.txt"]
+        verbose: true
+        pass_filenames: false

README.md

@@ -1,4 +1,5 @@
 [![Available on pypi](https://img.shields.io/pypi/v/seastats.svg)](https://pypi.python.org/pypi/seastats/)
+[![Conda Version](https://img.shields.io/conda/vn/conda-forge/seastats.svg)](https://anaconda.org/conda-forge/seastats)
 [![CI](https://github.com/oceanmodeling/seastats/actions/workflows/run_tests.yml/badge.svg)](https://github.com/oceanmodeling/seastats/actions/workflows/run_tests.yml)
 
 # SeaStats
@@ -15,7 +16,7 @@ def get_stats(
     obs: Series,
     metrics: Sequence[str] = SUGGESTED_METRICS,
     quantile: float = 0,
-    cluster: int = 72,
+    cluster: int = 24,
     round: int = -1
 ) -> dict[str, float]
 ```
@@ -54,7 +55,7 @@ Returns a dictionary containing the calculated metrics and their corresponding v
   * `mae`: Mean Absolute Error
   * `mse`: Mean Square Error
   * `nse`: Nash-Sutcliffe Efficiency
-  * `lamba`: Lambda index
+  * `lambda`: Lambda index
   * `cr`: Pearson Correlation coefficient
   * `cr_95`: Pearson Correlation coefficient for data points above 95th percentile
   * `slope`: Slope of Model/Obs correlation
@@ -140,7 +141,7 @@ with:
 NB: the function uses [pyextremes](https://georgebv.github.io/pyextremes/quickstart/) in the background, with PoT method, using the `quantile` value of the observed signal as physical threshold and passes the `cluster_duration` argument.
 
 
-this happens when the function `storms/match_extremes.py` couldn't finc concomitent storms for the observed and modeled time series.
+this happens when the function `storms/match_extremes.py` couldn't find concomitent storms for the observed and modeled time series.
 
 ## Usage
 see [notebook](/notebooks/example_abed.ipynb) for details
@@ -153,6 +154,6 @@ storm = get_stats(sim, obs, quantile = 0.99, metrics = STORM_METRICS) # we use a
 pd.DataFrame(dict(general, **storm), index=['abed'])
 ```
 
-|      |   bias |   rmse |   rms |   rms_95 |   sim_mean |   obs_mean |   sim_std |   obs_std |   nse |   lamba |    cr |   cr_95 |   slope |   intercept |   slope_pp |   intercept_pp |   mad |   madp |   madc |   kge |       R1 |   R1_norm |       R3 |   R3_norm |     error |   error_norm |
+|      |   bias |   rmse |   rms |   rms_95 |   sim_mean |   obs_mean |   sim_std |   obs_std |   nse |  lambda |    cr |   cr_95 |   slope |   intercept |   slope_pp |   intercept_pp |   mad |   madp |   madc |   kge |       R1 |   R1_norm |       R3 |   R3_norm |     error |   error_norm |
 |:-----|-------:|-------:|------:|---------:|-----------:|-----------:|----------:|----------:|------:|--------:|------:|--------:|--------:|------------:|-----------:|---------------:|------:|-------:|-------:|------:|---------:|----------:|---------:|----------:|----------:|-------------:|
 | abed | -0.007 |  0.086 | 0.086 |    0.088 |         -0 |      0.007 |     0.142 |     0.144 | 0.677 |   0.929 | 0.817 |   0.542 |   0.718 |      -0.005 |      1.401 |         -0.028 | 0.052 |  0.213 |  0.265 |  0.81 | 0.237364 |  0.295719 | 0.147163 |  0.207019 | 0.0938142 |     0.177533 |

notebooks/example_abed.ipynb

@@ -8,7 +8,7 @@
    "source": [
     "import pandas as pd\n",
     "import holoviews as hv\n",
-    "import hvplot.pandas\n",
+    "import hvplot.pandas  # noqa: F401\n",
     "\n",
     "from seastats import get_stats"
    ]
@@ -26,8 +26,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sim = pd.read_parquet('../tests/data/abed_sim.parquet')\n",
-    "obs = pd.read_parquet('../tests/data/abed_obs.parquet')"
+    "sim = pd.read_parquet(\"../tests/data/abed_sim.parquet\")\n",
+    "obs = pd.read_parquet(\"../tests/data/abed_obs.parquet\")"
    ]
   },
   {
@@ -47,7 +47,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "obs.hvplot(line_dash = \"dashed\") * sim.hvplot()"
+    "obs.hvplot(line_dash=\"dashed\") * sim.hvplot()"
    ]
   },
   {
@@ -67,6 +67,7 @@
    "outputs": [],
    "source": [
     "from seastats import GENERAL_METRICS, STORM_METRICS\n",
+    "\n",
     "GENERAL_METRICS\n",
     "STORM_METRICS"
    ]
@@ -78,7 +79,7 @@
    "outputs": [],
    "source": [
     "stats = get_stats(obs, sim)\n",
-    "pd.DataFrame(stats, index = ['abed'])"
+    "pd.DataFrame(stats, index=[\"abed\"])"
    ]
   },
   {
@@ -95,6 +96,7 @@
    "outputs": [],
    "source": [
     "from seastats import GENERAL_METRICS_ALL, STORM_METRICS_ALL\n",
+    "\n",
     "GENERAL_METRICS_ALL\n",
     "STORM_METRICS_ALL"
    ]
@@ -149,7 +151,7 @@
    "source": [
     "threshold = sim.quantile(quantile)\n",
     "ext_ = get_extremes(sim, \"POT\", threshold=threshold, r=f\"{cluster_duration}h\")\n",
-    "extremes1 = pd.DataFrame({\"modeled\" : ext_, \"time_model\" : ext_.index}, index=ext_.index)\n",
+    "extremes1 = pd.DataFrame({\"modeled\": ext_, \"time_model\": ext_.index}, index=ext_.index)\n",
     "ext_"
    ]
   },
@@ -178,7 +180,7 @@
    "source": [
     "threshold = obs.quantile(quantile)\n",
     "ext_ = get_extremes(obs, \"POT\", threshold=threshold, r=f\"{cluster_duration}h\")\n",
-    "extremes2 = pd.DataFrame({\"modeled\" : ext_, \"time_model\" : ext_.index}, index=ext_.index)\n",
+    "extremes2 = pd.DataFrame({\"modeled\": ext_, \"time_model\": ext_.index}, index=ext_.index)\n",
     "ext_"
    ]
   },
@@ -188,7 +190,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "obs_plot = obs.hvplot(line_dash = \"dashed\") * hv.Scatter((extremes2.index, extremes2.modeled)).opts(color=\"red\")\n",
+    "obs_plot = obs.hvplot(line_dash=\"dashed\") * hv.Scatter((extremes2.index, extremes2.modeled)).opts(\n",
+    "    color=\"red\",\n",
+    ")\n",
     "obs_plot"
    ]
   },
@@ -206,7 +210,8 @@
    "outputs": [],
    "source": [
     "from seastats.storms import match_extremes\n",
-    "extremes_df = match_extremes(sim, obs, 0.99, cluster = 72)\n",
+    "\n",
+    "extremes_df = match_extremes(sim, obs, 0.99, cluster=72)\n",
     "extremes_df"
    ]
   },
@@ -217,10 +222,14 @@
    "outputs": [],
    "source": [
     "hv.Points(\n",
-    "    extremes_df[['tdiff','diff']].rename(columns={'tdiff':'time difference (hours)','diff':'peak difference (m)'}), \n",
-    "    kdims=['time difference (hours)','peak difference (m)']).opts(\n",
-    "    size = 8, tools = ['hover']\n",
-    "    )"
+    "    extremes_df[[\"tdiff\", \"diff\"]].rename(\n",
+    "        columns={\"tdiff\": \"time difference (hours)\", \"diff\": \"peak difference (m)\"},\n",
+    "    ),\n",
+    "    kdims=[\"time difference (hours)\", \"peak difference (m)\"],\n",
+    ").opts(\n",
+    "    size=8,\n",
+    "    tools=[\"hover\"],\n",
+    ")"
    ]
   },
   {
@@ -244,7 +253,7 @@
    "outputs": [],
    "source": [
     "metrics = get_stats(sim, obs, quantile=0.99, cluster=72)\n",
-    "pd.DataFrame(dict(stats, **metrics), index=['abed'])"
+    "pd.DataFrame(dict(stats, **metrics), index=[\"abed\"])"
    ]
   }
  ],