Update isort, black, and remove nbqa-isort

Update .pre-commit-config.yaml Update .pre-commit-config.yaml Update .pre-commit-config.yaml Update .pre-commit-config.yaml Update .pre-commit-config.yaml Update .pre-commit-config.yaml Updated after lint check Updated after second lint check lint check third try lint check fourth try lint try 2 lint 3 Add not check lint for notebook 2 Add not check lint for notebook 3 Remove nbqa-isort
NCAR · Dec 11, 2023 · 9d706f7 · 9d706f7
1 parent f8dc393
commit 9d706f7
Show file tree

Hide file tree

Showing 9 changed files with 72 additions and 114 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -14,7 +14,7 @@ repos:
       - id: double-quote-string-fixer
 
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 23.10.1
     hooks:
       - id: black-jupyter
 
@@ -29,9 +29,10 @@ repos:
       - id: flake8
 
   - repo: https://github.com/PyCQA/isort
-    rev: 5.10.1
+    rev: 5.12.0
     hooks:
       - id: isort
+        args: ["--profile=black", "--filter-files"]
 
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v2.5.1
@@ -43,5 +44,5 @@ repos:
     hooks:
       - id: nbqa-pyupgrade
         additional_dependencies: [pyupgrade==2.7.3]
-      - id: nbqa-isort
-        additional_dependencies: [isort==5.6.4]
+      #- id: nbqa-isort
+      #  additional_dependencies: [isort==5.12.0]
diff --git a/notebooks/teopb_MPAS_ECT.ipynb b/notebooks/teopb_MPAS_ECT.ipynb
@@ -7,22 +7,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import numpy as np\n",
-    "import xarray as xr\n",
+    "import cartopy.crs as ccrs\n",
+    "import matplotlib.pyplot as plt\n",
     "import netCDF4 as nc\n",
-    "\n",
+    "import numpy as np\n",
     "import seaborn as sns\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
     "import statsmodels.api as sm\n",
+    "import xarray as xr\n",
     "from scipy.stats import shapiro\n",
-    "\n",
-    "# import PyCECT.pyEnsLib as PEL\n",
     "from os import listdir\n",
     "from os.path import isfile, join\n",
-    "\n",
-    "import cartopy.crs as ccrs\n",
-    "\n",
+    "import PyCECT.pyEnsLib as PEL\n",
     "import re"
    ]
   },
@@ -34,7 +29,7 @@
    "outputs": [],
    "source": [
     "summ_path = \"/glade/work/abaker/mpas_data/100_ens_summary\"\n",
-    "summ_files = [summ_path+\"/mpas_sum_ts\"+str(i)+\".nc\" for i in [6, 9, 12, 15, 18]]\n",
+    "summ_files = [summ_path + \"/mpas_sum_ts\" + str(i) + \".nc\" for i in [6, 9, 12, 15, 18]]\n",
     "test_summary = xr.open_dataset(summ_files[0])\n",
     "var_strings = np.char.rstrip(np.char.decode(test_summary.vars))"
    ]
@@ -62,19 +57,19 @@
     "# Correlation Plots\n",
     "\n",
     "summ_path = \"/glade/work/abaker/mpas_data/100_ens_summary\"\n",
-    "summ_files = [summ_path+\"/mpas_sum_ts\"+str(i)+\".nc\" for i in [6, 9, 12, 15, 18]]\n",
+    "summ_files = [summ_path + \"/mpas_sum_ts\" + str(i) + \".nc\" for i in [6, 9, 12, 15, 18]]\n",
     "\n",
-    "cutoff = .85\n",
+    "cutoff = 0.85\n",
     "\n",
     "fig, axs = plt.subplots(len(summ_files), figsize=(10, 40))\n",
     "\n",
     "for i, f in enumerate(summ_files):\n",
     "    test_summary = xr.open_dataset(f)\n",
     "    corr = np.corrcoef(test_summary.global_mean)\n",
     "    sns.heatmap(corr, vmin=-1, vmax=1, ax=axs[i])\n",
-    "    axs[i].set_title(\"Timeslice = \" + str(i*3 + 6))\n",
-    "    \n",
-    "    correlated_entries = np.argwhere((corr > cutoff)|(corr < -cutoff))\n",
+    "    axs[i].set_title(\"Timeslice = \" + str(i * 3 + 6))\n",
+    "\n",
+    "    correlated_entries = np.argwhere((corr > cutoff) | (corr < -cutoff))\n",
     "    filt_correlated_entries = []\n",
     "    for i in correlated_entries:\n",
     "        if i[0] != i[1]:\n",
@@ -180,15 +175,15 @@
     "\n",
     "test_summary = xr.open_dataset(summ_files[0])\n",
     "\n",
-    "fig, axs = plt.subplots(11, 6, sharex=True, figsize=(16,16))\n",
+    "fig, axs = plt.subplots(11, 6, sharex=True, figsize=(16, 16))\n",
     "for i in range(len(var_strings)):\n",
-    "    row = i//6\n",
+    "    row = i // 6\n",
     "    col = i % 6\n",
     "    sm.qqplot(test_summary.global_mean[i, :], ax=axs[row, col], fit=True, line=\"45\")\n",
     "    axs[row, col].set_title(var_strings[i])\n",
     "\n",
     "for i in range(len(var_strings), 11 * 6):\n",
-    "    row = i//6\n",
+    "    row = i // 6\n",
     "    col = i % 6\n",
     "    axs[row, col].axis('off')\n",
     "\n",
@@ -760,7 +755,7 @@
    ],
    "source": [
     "test_summary = xr.open_dataset(summ_files[0])\n",
-    "plt.hist(test_summary.global_mean[0,:], bins=20)"
+    "plt.hist(test_summary.global_mean[0, :], bins=20)"
    ]
   },
   {
@@ -801,7 +796,7 @@
    ],
    "source": [
     "test_summary = xr.open_dataset(summ_files[1])\n",
-    "plt.hist(test_summary.global_mean[0,:], bins=20)"
+    "plt.hist(test_summary.global_mean[0, :], bins=20)"
    ]
   },
   {
@@ -842,7 +837,7 @@
    ],
    "source": [
     "test_summary = xr.open_dataset(summ_files[2])\n",
-    "plt.hist(test_summary.global_mean[0,:], bins=20)"
+    "plt.hist(test_summary.global_mean[0, :], bins=20)"
    ]
   },
   {
@@ -882,7 +877,7 @@
     }
    ],
    "source": [
-    "plt.hist(test_summary.global_mean[0,:], bins=20)"
+    "plt.hist(test_summary.global_mean[0, :], bins=20)"
    ]
   },
   {
@@ -893,7 +888,7 @@
    "outputs": [],
    "source": [
     "hist_path = \"/glade/scratch/abaker/mpas_hist\"\n",
-    "hist_files = [hist_path+\"/history.\"+str(i).zfill(3)+\".nc\" for i in range(100)]"
+    "hist_files = [hist_path + \"/history.\" + str(i).zfill(3) + \".nc\" for i in range(100)]"
    ]
   },
   {
@@ -933,32 +928,31 @@
    "source": [
     "def plot_vars(data, lats, lons, title, unit, save=False, filename=None):\n",
     "    plt.clf()\n",
-    "    \n",
+    "\n",
     "    cmap = sns.color_palette(\"flare\", as_cmap=True)\n",
-    "    \n",
+    "\n",
     "    # f, ax = plt.subplots(figsize=(15, 10))\n",
-    "    \n",
+    "\n",
     "    f, ax = plt.subplots(figsize=(15, 10), subplot_kw={'projection': ccrs.Robinson()})\n",
-    "    \n",
+    "\n",
     "    ax.coastlines(alpha=0.3)\n",
-    "    \n",
+    "\n",
     "    # points = ax.scatter(x=lons, y=lats, c=data, s=7, cmap=cmap)\n",
-    "    \n",
-    "#     convert from radians to degrees\n",
+    "\n",
+    "    #     convert from radians to degrees\n",
     "\n",
     "    lats = lats * 180 / np.pi\n",
     "    lons = lons * 180 / np.pi\n",
     "    lons = ((lons - 180.0) % 360.0) - 180.0\n",
-    "    \n",
+    "\n",
     "    points = ax.scatter(x=lons, y=lats, c=data, s=7, cmap=cmap, transform=ccrs.PlateCarree())\n",
-    "    \n",
-    "    f.colorbar(points, label = unit)\n",
-    "    \n",
+    "\n",
+    "    f.colorbar(points, label=unit)\n",
+    "\n",
     "    plt.title(title)\n",
     "    plt.xlabel(\"Longitude (rad)\")\n",
     "    plt.ylabel(\"Latitude (rad)\")\n",
-    "    \n",
-    "    \n",
+    "\n",
     "    if filename != None:\n",
     "        plt.savefig(filename)\n",
     "        plt.close('all')\n",
@@ -1003,7 +997,7 @@
     "        all_hist_vars.append(get_var_timeslice(data, var_name, time_slice).data)\n",
     "\n",
     "    stacked_vars = np.vstack(all_hist_vars)\n",
-    "    \n",
+    "\n",
     "    if opp_name == \"mean\":\n",
     "        trans_var = np.mean(stacked_vars, axis=0)\n",
     "        title = \"Mean \" + title\n",
@@ -1017,8 +1011,8 @@
     "        trans_var = np.amax(stacked_vars, axis=0)\n",
     "        title = \"Max \" + title\n",
     "    if filepath != None:\n",
-    "        filename = \"global_\"+var_name +\"_\" +opp_name+ \"_\" + \"t\"+ str(time_slice)+\".png\"\n",
-    "        filename = filepath +\"/\" + filename\n",
+    "        filename = \"global_\" + var_name + \"_\" + opp_name + \"_\" + \"t\" + str(time_slice) + \".png\"\n",
+    "        filename = filepath + \"/\" + filename\n",
     "        plot_vars(trans_var, lats, lons, title, units, filename=filename)\n",
     "    else:\n",
     "        plot_vars(trans_var, lats, lons, title, units)"
@@ -1341,9 +1335,9 @@
     "        all_hist_vars.append(get_var_timeslice(data, var_name, time_slice).data)\n",
     "\n",
     "    stacked_vars = np.vstack(all_hist_vars)\n",
-    "    \n",
+    "\n",
     "    _, cell_count = stacked_vars.shape\n",
-    "    \n",
+    "\n",
     "    if opp_name == \"mean\":\n",
     "        trans_var = np.mean(stacked_vars, axis=0)\n",
     "        title = \"Mean \" + title\n",
@@ -1356,38 +1350,40 @@
     "    elif opp_name == \"max\":\n",
     "        trans_var = np.amax(stacked_vars, axis=0)\n",
     "        title = \"Max \" + title\n",
-    "        \n",
-    "#     Create histogram of nonzero transformed variable cells (aka cells where peak to peak is greater than zero)\n",
-    "#     Actually plot bins after first of 100 to enable viewing relevant values.\n",
+    "\n",
+    "    #     Create histogram of nonzero transformed variable cells (aka cells where peak to peak is greater than zero)\n",
+    "    #     Actually plot bins after first of 100 to enable viewing relevant values.\n",
     "    nonzero = np.count_nonzero(trans_var)\n",
-    "    n, bins, patches= plt.hist(trans_var, bins=100)\n",
+    "    n, bins, patches = plt.hist(trans_var, bins=100)\n",
     "    plt.clf()\n",
     "    plt.hist(trans_var[trans_var > bins[1]], bins=99)\n",
-    "    title_str = f\"{title} \\n Cell {opp_name} Hist > {bins[1]:.4f}, Nonzero: {(nonzero/cell_count)*100:.1f}%\"\n",
+    "    title_str = (\n",
+    "        f\"{title} \\n Cell {opp_name} Hist > {bins[1]:.4f}, Nonzero: {(nonzero/cell_count)*100:.1f}%\"\n",
+    "    )\n",
     "    x_label = f\"{opp_name} {units}\"\n",
     "    plt.xlabel(x_label)\n",
     "    plt.title(title_str)\n",
-    "    \n",
+    "\n",
     "    if filepath != None:\n",
     "        filename = f\"{var_name}_{opp_name}_hist_t_{str(time_slice)}.png\"\n",
-    "        filename = filepath +\"/\" + filename\n",
+    "        filename = filepath + \"/\" + filename\n",
     "        plt.savefig(filename)\n",
     "        plt.clf()\n",
     "    else:\n",
     "        plt.show()\n",
-    "    \n",
-    "#     Get cell indices in last bin\n",
-    "    n_last  = n[-1]\n",
+    "\n",
+    "    #     Get cell indices in last bin\n",
+    "    n_last = n[-1]\n",
     "    cell_idx = np.argwhere(trans_var > bins[-2])[0][0]\n",
     "    plt.hist(stacked_vars[:, cell_idx], bins=100)\n",
     "    title_str = f\"{title} \\n Hist of cell in top {opp_name} bin (1 of {int(n_last)})\"\n",
     "    plt.title(title_str)\n",
     "    x_label = f\"{units}\"\n",
     "    plt.xlabel(x_label)\n",
-    "    \n",
+    "\n",
     "    if filepath != None:\n",
     "        filename = f\"{var_name}_{opp_name}_tophist_t_{str(time_slice)}.png\"\n",
-    "        filename = filepath +\"/\" + filename\n",
+    "        filename = filepath + \"/\" + filename\n",
     "        plt.savefig(filename)\n",
     "        plt.clf()\n",
     "    else:\n",
@@ -1451,7 +1447,9 @@
     "for t in [6, 18]:\n",
     "    for name in var_strings:\n",
     "        try:\n",
-    "            ensemble_variance_cause(hist_files, name, t, \"ptp\", filepath=\"/glade/u/home/teopb/figures\")\n",
+    "            ensemble_variance_cause(\n",
+    "                hist_files, name, t, \"ptp\", filepath=\"/glade/u/home/teopb/figures\"\n",
+    "            )\n",
     "        except:\n",
     "            print(f\"issue with {name}\")"
    ]
@@ -1465,6 +1463,8 @@
    "source": [
     "# Spread of ensemble global mean over time\n",
     "long_summ_filepath = \"/glade/work/abaker/mpas_data/100_ens_summary/\"\n",
+    "\n",
+    "\n",
     "def gm_time_spread(long_summ_filepath, hist_file, var_name=None, filepath=None):\n",
     "    summ_files = [fn for fn in listdir(long_summ_filepath) if fn.endswith(\".nc\")]\n",
     "\n",
@@ -1481,7 +1481,7 @@
     "    time_size = len(timesteps)\n",
     "\n",
     "    temp_array = np.empty((time_size, var_size, ens_size))\n",
-    "    \n",
+    "\n",
     "    hist_data = xr.open_dataset(hist_file)\n",
     "\n",
     "    for t, step in enumerate(timesteps):\n",
@@ -1490,33 +1490,33 @@
     "        data = xr.open_dataset(file_name)\n",
     "        # print(data.global_mean.shape)\n",
     "        for v in range(len(var_names)):\n",
-    "            temp_array[t, v, :] = data.global_mean[v,:]\n",
+    "            temp_array[t, v, :] = data.global_mean[v, :]\n",
     "\n",
     "    means = np.mean(temp_array, axis=2)\n",
-    "    \n",
-    "#     Plot 1 variable and display\n",
+    "\n",
+    "    #     Plot 1 variable and display\n",
     "    if var_name != None:\n",
     "        title, units = get_info(hist_data, var_name, timesteps[0])\n",
     "        var_idx = np.where(var_names == var_name)[0][0]\n",
     "        plt.clf()\n",
     "        for i in range(ens_size):\n",
     "            diff = temp_array[:, var_idx, i] - means[:, var_idx]\n",
-    "            plt.plot(timesteps, diff, alpha=.5)\n",
-    "        \n",
+    "            plt.plot(timesteps, diff, alpha=0.5)\n",
+    "\n",
     "        title_str = f\"{title} Ensemble Spread From Mean\"\n",
     "        x_label = \"Timestep\"\n",
     "        plt.xlabel(x_label)\n",
     "        plt.title(title_str)\n",
     "        plt.show()\n",
-    "    \n",
-    "#     Plot all variables and save at filepath\n",
+    "\n",
+    "    #     Plot all variables and save at filepath\n",
     "    if filepath != None:\n",
     "        for var_idx, var_name in enumerate(var_names):\n",
     "            try:\n",
     "                title, units = get_info(hist_data, var_name, timesteps[0])\n",
     "                for i in range(ens_size):\n",
     "                    diff = temp_array[:, var_idx, i] - means[:, var_idx]\n",
-    "                    plt.plot(timesteps, diff, alpha=.5)\n",
+    "                    plt.plot(timesteps, diff, alpha=0.5)\n",
     "\n",
     "                title_str = f\"{title} Ensemble Spread From Mean\"\n",
     "                x_label = \"Timestep\"\n",