From 2028c4ec8acac9c33f83dcaf606647c2c8de083b Mon Sep 17 00:00:00 2001 From: Oriol Abril-Pla Date: Mon, 16 Jan 2023 23:36:06 +0100 Subject: [PATCH] prepare release of version 0.5.0 (#41) --- docs/source/changelog.md | 2 +- .../source/tutorials/einops-basics-port.ipynb | 16 +- docs/source/tutorials/linalg_tutorial.ipynb | 96 ++++---- .../tutorials/np_linalg_tutorial_port.ipynb | 56 ++--- docs/source/tutorials/stats_tutorial.ipynb | 224 +++++++++--------- src/xarray_einstats/__init__.py | 2 +- 6 files changed, 194 insertions(+), 202 deletions(-) diff --git a/docs/source/changelog.md b/docs/source/changelog.md index 740d1de..08cdd68 100644 --- a/docs/source/changelog.md +++ b/docs/source/changelog.md @@ -1,6 +1,6 @@ # Change Log -## v0.x.x (Unreleased) +## v0.5.0 (2023 Jan 16) ### New features * Added {func}`.empty_ref`, {func}`.ones_ref` and {func}`.zeros_ref` DataArray creation helpers {pull}`37` * Added {func}`.linalg.diagonal` wrapper {pull}`37` diff --git a/docs/source/tutorials/einops-basics-port.ipynb b/docs/source/tutorials/einops-basics-port.ipynb index e28bba2..f6790ea 100644 --- a/docs/source/tutorials/einops-basics-port.ipynb +++ b/docs/source/tutorials/einops-basics-port.ipynb @@ -448,7 +448,7 @@ "Dimensions: (batch: 6, height: 96, width: 96, channel: 3)\n", "Dimensions without coordinates: batch, height, width, channel\n", "Data variables:\n", - " ims (batch, height, width, channel) float64 1.0 0.902 ... 1.0 0.8039
      • " ], "text/plain": [ "\n", @@ -1693,17 +1693,17 @@ "name": "stdout", "output_type": "stream", "text": [ - "Last updated: Fri Dec 09 2022\n", + "Last updated: Mon Jan 16 2023\n", "\n", "Python implementation: CPython\n", - "Python version : 3.9.13\n", - "IPython version : 8.4.0\n", + "Python version : 3.10.8\n", + "IPython version : 8.7.0\n", "\n", "einops : 0.6.0\n", - "xarray_einstats: 0.4.0\n", + "xarray_einstats: 0.5.0\n", "\n", + "numpy : 1.24.0\n", "xarray: 2022.12.0\n", - "numpy : 1.23.5\n", "\n", "Watermark: 2.3.1\n", "\n" @@ -1739,7 +1739,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.13" + "version": "3.10.8" } }, "nbformat": 4, diff --git a/docs/source/tutorials/linalg_tutorial.ipynb b/docs/source/tutorials/linalg_tutorial.ipynb index caccddf..b0ef4f3 100644 --- a/docs/source/tutorials/linalg_tutorial.ipynb +++ b/docs/source/tutorials/linalg_tutorial.ipynb @@ -403,7 +403,7 @@ "}\n", "
      <xarray.DataArray (batch: 10, experiment: 3, dim: 4, dim2: 4)>\n",
        "0.7075 1.025 0.5685 0.8951 0.2065 3.384 ... 1.239 0.4527 0.5749 0.4766 0.859\n",
-       "Dimensions without coordinates: batch, experiment, dim, dim2
          • " ], "text/plain": [ "\n", @@ -847,7 +847,7 @@ "}\n", "
          <xarray.DataArray (batch: 10, experiment: 3)>\n",
        "4.854 4.74 4.457 2.637 2.79 3.163 1.998 ... 2.804 4.58 2.888 4.936 5.983 4.07\n",
-       "Dimensions without coordinates: batch, experiment
              • " ], "text/plain": [ "\n", @@ -1255,7 +1255,7 @@ "}\n", "
              <xarray.DataArray (batch: 10, experiment: 3, dim: 4, dim2: 4)>\n",
        "11.26 -2.363 -10.84 -0.2744 10.99 -2.017 ... -3.444 0.7703 0.316 0.01949 -1.162\n",
-       "Dimensions without coordinates: batch, experiment, dim, dim2
                  • " ], "text/plain": [ "\n", @@ -1704,7 +1704,7 @@ "}\n", "
                  <xarray.DataArray (batch: 10, experiment: 3, dim: 4, dim2: 4)>\n",
        "-0.5452 0.01652 -0.5624 -0.6214 -0.1592 ... -0.3322 -0.4013 0.2607 0.8128\n",
-       "Dimensions without coordinates: batch, experiment, dim, dim2
                      • " ], "text/plain": [ "\n", @@ -2135,7 +2135,7 @@ "}\n", "
                      <xarray.DataArray (batch: 10, experiment: 3, dim: 4, dim2: 4)>\n",
        "-1.298 -1.975 -1.858 -1.228 0.0 -3.137 ... -0.4307 1.052 0.0 0.0 0.0 -0.6995\n",
-       "Dimensions without coordinates: batch, experiment, dim, dim2
                          • " ], "text/plain": [ "\n", @@ -2612,7 +2612,7 @@ "}\n", "
                          <xarray.DataArray (batch: 10, experiment: 3, dim: 4, dim2: 4)>\n",
        "1.845 5.326 2.407 3.89 3.378 14.68 5.449 ... 5.586 6.55 1.279 1.373 1.791 2.658\n",
-       "Dimensions without coordinates: batch, experiment, dim, dim2
                              • " ], "text/plain": [ "\n", @@ -3063,7 +3063,7 @@ "}\n", "
                              <xarray.DataArray (dim: 4, dim2_bis: 4, batch_bis: 10, batch: 10, dim2: 4)>\n",
        "10.79 3.926 1.503 3.986 0.1886 0.1844 ... 1.289 4.187 5.251 3.372 2.81 13.1\n",
-       "Dimensions without coordinates: dim, dim2_bis, batch_bis, batch, dim2
                                  • " ], "text/plain": [ "\n", @@ -3505,7 +3505,7 @@ "}\n", "
                                  <xarray.DataArray (dim: 4, dim2: 4, batch: 10, batch2: 10)>\n",
        "10.79 0.1886 5.402 1.471 1.243 5.348 2.639 ... 3.462 3.618 11.21 9.47 4.187 13.1\n",
-       "Dimensions without coordinates: dim, dim2, batch, batch2
                                      • " ], "text/plain": [ "\n", @@ -3947,7 +3947,7 @@ "}\n", "
                                      <xarray.DataArray (batch: 10, experiment: 3, different_dim: 4, different_dim2: 4)>\n",
        "0.7075 1.025 0.5685 0.8951 0.2065 3.384 ... 1.239 0.4527 0.5749 0.4766 0.859\n",
-       "Dimensions without coordinates: batch, experiment, different_dim, different_dim2
                                          • " ], "text/plain": [ "\n", @@ -4387,7 +4387,7 @@ "}\n", "
                                          <xarray.DataArray (batch: 10, experiment: 3, dim: 4, different_dim2: 4)>\n",
        "1.845 5.326 2.407 3.89 3.378 14.68 5.449 ... 5.586 6.55 1.279 1.373 1.791 2.658\n",
-       "Dimensions without coordinates: batch, experiment, dim, different_dim2
                                              • " ], "text/plain": [ "\n", @@ -4826,7 +4826,7 @@ "}\n", "
                                              <xarray.DataArray (dim: 4, dim2: 4, experiment: 3, experiment2: 3)>\n",
        "9.727 6.68 3.595 6.68 18.66 6.065 3.595 ... 10.81 36.08 8.181 3.233 8.181 14.77\n",
-       "Dimensions without coordinates: dim, dim2, experiment, experiment2
                                                  • " ], "text/plain": [ "\n", @@ -5292,7 +5292,7 @@ "}\n", "
                                                  <xarray.DataArray (batch: 10, dim: 4, dim2: 4)>\n",
        "4.487 3.158 0.9252 2.683 0.5319 3.799 ... 3.387 1.796 2.601 2.455 1.538 5.402\n",
-       "Dimensions without coordinates: batch, dim, dim2
                                                      • " ], "text/plain": [ "\n", @@ -5732,10 +5732,10 @@ "}\n", "
                                                      <xarray.DataArray (dim: 4, dim2: 4)>\n",
        "22.27 32.55 29.06 40.96 23.96 33.48 ... 25.27 29.59 34.97 20.57 34.89 30.26\n",
-       "Dimensions without coordinates: dim, dim2
                                                          • " ], "text/plain": [ "\n", @@ -6148,7 +6148,7 @@ "}\n", "
                                                          <xarray.DataArray (batch: 10, dim: 4, dim2: 4)>\n",
        "10.79 3.543 0.4447 2.399 0.111 11.58 10.95 ... 5.104 1.799 2.513 3.052 0.79 13.1\n",
-       "Dimensions without coordinates: batch, dim, dim2
                                                              • " ], "text/plain": [ "\n", @@ -6602,7 +6602,7 @@ "}\n", "
                                                              <xarray.DataArray (dim: 4, dim2: 4, batch: 10, experiment: 3)>\n",
        "33.15 44.26 22.52 1.318 1.76 0.8951 ... 19.52 36.93 18.42 42.62 80.64 40.23\n",
-       "Dimensions without coordinates: dim, dim2, batch, experiment
                                                                  • " ], "text/plain": [ "\n", @@ -7060,10 +7060,10 @@ "}\n", "
                                                                  <xarray.DataArray (dim: 4, dim2: 4)>\n",
        "496.0 1.06e+03 844.2 1.678e+03 573.9 ... 875.4 1.223e+03 423.1 1.218e+03 915.8\n",
-       "Dimensions without coordinates: dim, dim2
                                                                      • " ], "text/plain": [ "\n", @@ -7481,10 +7481,10 @@ "}\n", "
                                                                      <xarray.DataArray (dim: 4, dim2: 4)>\n",
        "32.03 68.57 42.6 101.0 40.06 76.88 59.44 ... 33.78 83.88 72.41 32.43 76.33 60.63\n",
-       "Dimensions without coordinates: dim, dim2
                                                                          • " ], "text/plain": [ "\n", @@ -7883,10 +7883,10 @@ "}\n", "
                                                                          <xarray.DataArray (dim: 4, dim2: 4)>\n",
        "32.03 68.57 42.6 101.0 40.06 76.88 59.44 ... 33.78 83.88 72.41 32.43 76.33 60.63\n",
-       "Dimensions without coordinates: dim, dim2
                                                                              • " ], "text/plain": [ "\n", @@ -8301,7 +8301,7 @@ "}\n", "
                                                                              <xarray.DataArray (batch: 10, experiment: 3, dim: 4)>\n",
        "2.676 19.38 0.8116 5.562 11.33 2.104 ... 6.259 12.24 6.737 0.5945 7.355 1.5\n",
-       "Dimensions without coordinates: batch, experiment, dim
                                                                                  • " ], "text/plain": [ "\n", @@ -8739,7 +8739,7 @@ "}\n", "
                                                                                  <xarray.DataArray (batch: 10, experiment: 3, dim: 4, dim_auto2: 4)>\n",
        "2.676 6.135 1.302 3.007 6.135 19.38 2.018 ... 7.355 2.884 2.942 0.8866 2.884 1.5\n",
-       "Dimensions without coordinates: batch, experiment, dim, dim_auto2
                                                                                      • " ], "text/plain": [ "\n", @@ -9185,7 +9185,7 @@ "}\n", "
                                                                                      <xarray.DataArray (experiment: 3, dim: 4, dim2: 4, batch: 10, batch2: 10)>\n",
        "0.5006 0.09001 0.1315 0.3874 0.5949 0.6645 ... 2.931 0.2908 0.5802 0.4342 0.7379\n",
-       "Dimensions without coordinates: experiment, dim, dim2, batch, batch2
                                                                                          • " ], "text/plain": [ "\n", @@ -9252,16 +9252,16 @@ "name": "stdout", "output_type": "stream", "text": [ - "Last updated: Fri Dec 09 2022\n", + "Last updated: Mon Jan 16 2023\n", "\n", "Python implementation: CPython\n", - "Python version : 3.9.13\n", - "IPython version : 8.4.0\n", + "Python version : 3.10.8\n", + "IPython version : 8.7.0\n", "\n", - "numpy: 1.23.5\n", + "numpy: 1.24.0\n", "\n", "xarray : 2022.12.0\n", - "xarray_einstats: 0.4.0\n", + "xarray_einstats: 0.5.0\n", "\n", "Watermark: 2.3.1\n", "\n" @@ -9290,7 +9290,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.13" + "version": "3.10.8" } }, "nbformat": 4, diff --git a/docs/source/tutorials/np_linalg_tutorial_port.ipynb b/docs/source/tutorials/np_linalg_tutorial_port.ipynb index cad86ba..01fa3ad 100644 --- a/docs/source/tutorials/np_linalg_tutorial_port.ipynb +++ b/docs/source/tutorials/np_linalg_tutorial_port.ipynb @@ -42,7 +42,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "/tmp/ipykernel_24412/849063265.py:6: DeprecationWarning: scipy.misc.face has been deprecated in SciPy v1.10.0; and will be completely removed in SciPy v1.12.0. Dataset methods have moved into the scipy.datasets module. Use scipy.datasets.face instead.\n", + "/tmp/ipykernel_39843/849063265.py:6: DeprecationWarning: scipy.misc.face has been deprecated in SciPy v1.10.0; and will be completely removed in SciPy v1.12.0. Dataset methods have moved into the scipy.datasets module. Use scipy.datasets.face instead.\n", " img = xr.DataArray(misc.face(), dims=[\"height\", \"width\", \"color\"], coords={\"color\": [\"R\", \"G\", \"B\"]})\n" ] } @@ -556,7 +556,7 @@ "121 112 131 138 129 148 153 144 165 155 ... 98 120 156 95 119 155 93 118 154 92\n", "Coordinates:\n", " * color (color) <U1 'R' 'G' 'B'\n", - "Dimensions without coordinates: height, width
                                                                                          • color
                                                                                            (color)
                                                                                            <U1
                                                                                            'R' 'G' 'B'
                                                                                            array(['R', 'G', 'B'], dtype='<U1')
                                                                                          • color
                                                                                            PandasIndex
                                                                                            PandasIndex(Index(['R', 'G', 'B'], dtype='object', name='color'))
                                                                                          • " ], "text/plain": [ "\n", @@ -1004,13 +1004,13 @@ "121 138 153 155 155 158 159 156 147 137 ... 113 116 117 120 121 121 120 119 118\n", "Coordinates:\n", " color <U1 'R'\n", - "Dimensions without coordinates: height, width
                                                                                          • color
                                                                                            ()
                                                                                            <U1
                                                                                            'R'
                                                                                            array('R', dtype='<U1')
                                                                                            • " ], "text/plain": [ "\n", @@ -1562,7 +1562,7 @@ "}\n", "
                                                                                            <xarray.DataArray (height: 768, width: 1024)>\n",
        "0.4521 0.5188 0.5782 0.586 0.586 0.5955 ... 0.5667 0.5662 0.5645 0.5603 0.5564\n",
-       "Dimensions without coordinates: height, width
                                                                                                • " ], "text/plain": [ "\n", @@ -2032,7 +2032,7 @@ "}\n", "
                                                                                                <xarray.DataArray (height: 768, height2: 768)>\n",
        "0.03181 0.01899 0.01773 0.00738 0.01887 ... 0.03089 0.005258 0.0146 0.004079\n",
-       "Dimensions without coordinates: height, height2
                                                                                                    • " ], "text/plain": [ "\n", @@ -2435,7 +2435,7 @@ "}\n", "
                                                                                                    <xarray.DataArray (height: 768)>\n",
        "410.4 85.56 63.61 45.85 41.97 38.26 ... 0.01117 0.01085 0.01079 0.01032 0.009925\n",
-       "Dimensions without coordinates: height
                                                                                                        • " ], "text/plain": [ "\n", @@ -2866,7 +2866,7 @@ "}\n", "
                                                                                                        <xarray.DataArray (width: 1024, width2: 1024)>\n",
        "0.03587 0.03582 0.03581 0.03574 0.03553 ... 0.03706 0.0731 -0.2073 0.1374\n",
-       "Dimensions without coordinates: width, width2
                                                                                                            • " ], "text/plain": [ "\n", @@ -3294,7 +3294,7 @@ "}\n", "
                                                                                                            <xarray.DataArray (height: 768, width: 1024)>\n",
        "410.4 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0\n",
-       "Dimensions without coordinates: height, width
                                                                                                                • " ], "text/plain": [ "\n", @@ -3714,7 +3714,7 @@ " fill: currentColor;\n", "}\n", "
                                                                                                                <xarray.DataArray ()>\n",
-       "1.429e-12
                                                                                                                " + "1.429e-12" ], "text/plain": [ "\n", @@ -4192,7 +4192,7 @@ "}\n", "
                                                                                                                <xarray.DataArray (height: 768, width: 10)>\n",
        "410.4 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0\n",
-       "Dimensions without coordinates: height, width
                                                                                                                    • " ], "text/plain": [ "\n", @@ -4595,7 +4595,7 @@ "}\n", "
                                                                                                                    <xarray.DataArray (width: 10, width2: 1024)>\n",
        "0.03587 0.03582 0.03581 0.03574 0.03553 ... -0.07889 -0.07779 -0.07644 -0.07542\n",
-       "Dimensions without coordinates: width, width2
                                                                                                                        • " ], "text/plain": [ "\n", @@ -5124,7 +5124,7 @@ "0.4745 0.5412 0.6 0.6078 0.6078 0.6196 ... 0.3922 0.3843 0.3725 0.3647 0.3608\n", "Coordinates:\n", " * color (color) <U1 'R' 'G' 'B'\n", - "Dimensions without coordinates: height, width
                                                                                                                        • color
                                                                                                                          (color)
                                                                                                                          <U1
                                                                                                                          'R' 'G' 'B'
                                                                                                                          array(['R', 'G', 'B'], dtype='<U1')
                                                                                                                        • color
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Index(['R', 'G', 'B'], dtype='object', name='color'))
                                                                                                                        • " ], "text/plain": [ "\n", @@ -5661,7 +5661,7 @@ "0.4745 0.4822 0.4893 0.492 0.4967 0.5061 ... 0.2838 0.2866 0.2899 0.2925 0.2938\n", "Coordinates:\n", " * color (color) <U1 'R' 'G' 'B'\n", - "Dimensions without coordinates: height, width
                                                                                                                        • color
                                                                                                                          (color)
                                                                                                                          <U1
                                                                                                                          'R' 'G' 'B'
                                                                                                                          array(['R', 'G', 'B'], dtype='<U1')
                                                                                                                        • color
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Index(['R', 'G', 'B'], dtype='object', name='color'))
                                                                                                                        • " ], "text/plain": [ "\n", @@ -5793,11 +5793,11 @@ "Python version : 3.10.8\n", "IPython version : 8.7.0\n", "\n", - "scipy : 1.10.0rc1\n", - "xarray_einstats: 0.5.0.dev0\n", - "xarray : 2022.12.0\n", - "matplotlib : 3.6.2\n", + "xarray_einstats: 0.5.0\n", "numpy : 1.24.0\n", + "matplotlib : 3.6.2\n", + "scipy : 1.10.0\n", + "xarray : 2022.12.0\n", "\n", "Watermark: 2.3.1\n", "\n" diff --git a/docs/source/tutorials/stats_tutorial.ipynb b/docs/source/tutorials/stats_tutorial.ipynb index 3608ec2..daac143 100644 --- a/docs/source/tutorials/stats_tutorial.ipynb +++ b/docs/source/tutorials/stats_tutorial.ipynb @@ -439,56 +439,56 @@ " fill: currentColor;\n", "}\n", "
                                                                                                                        <xarray.DataArray (rv_dim0: 10, chain: 4, draw: 10, team: 6)>\n",
-       "-0.06616 0.3246 1.037 -0.1329 -0.06425 ... 0.005495 0.3913 0.3253 0.2695 2.053\n",
+       "0.6418 0.4174 1.425 0.05737 0.5546 4.485 ... 0.1927 -0.3864 0.2633 0.3151 1.68\n",
        "Coordinates:\n",
        "  * team     (team) <U1 'a' 'b' 'c' 'd' 'e' 'f'\n",
        "  * chain    (chain) int64 0 1 2 3\n",
        "  * draw     (draw) int64 0 1 2 3 4 5 6 7 8 9\n",
-       "Dimensions without coordinates: rv_dim0
                                                                                                                        • team
                                                                                                                          (team)
                                                                                                                          <U1
                                                                                                                          'a' 'b' 'c' 'd' 'e' 'f'
                                                                                                                          array(['a', 'b', 'c', 'd', 'e', 'f'], dtype='<U1')
                                                                                                                        • chain
                                                                                                                          (chain)
                                                                                                                          int64
                                                                                                                          0 1 2 3
                                                                                                                          array([0, 1, 2, 3])
                                                                                                                        • draw
                                                                                                                          (draw)
                                                                                                                          int64
                                                                                                                          0 1 2 3 4 5 6 7 8 9
                                                                                                                          array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
                                                                                                                        • team
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Index(['a', 'b', 'c', 'd', 'e', 'f'], dtype='object', name='team'))
                                                                                                                        • chain
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3], dtype='int64', name='chain'))
                                                                                                                        • draw
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype='int64', name='draw'))
                                                                                                                        • " ], "text/plain": [ "\n", - "-0.06616 0.3246 1.037 -0.1329 -0.06425 ... 0.005495 0.3913 0.3253 0.2695 2.053\n", + "0.6418 0.4174 1.425 0.05737 0.5546 4.485 ... 0.1927 -0.3864 0.2633 0.3151 1.68\n", "Coordinates:\n", " * team (team) 
                                                                                                                        <xarray.DataArray (subject: 5, batch: 3, chain: 4, draw: 10, team: 6)>\n",
-       "0.02322 0.252 1.428 0.06006 0.01792 ... 0.3755 -0.1818 0.1006 0.06794 1.643\n",
+       "0.2426 0.2904 0.6682 -0.1603 0.02198 ... -0.102 -0.08568 0.4546 0.2521 1.719\n",
        "Coordinates:\n",
        "  * team     (team) <U1 'a' 'b' 'c' 'd' 'e' 'f'\n",
        "  * chain    (chain) int64 0 1 2 3\n",
        "  * draw     (draw) int64 0 1 2 3 4 5 6 7 8 9\n",
-       "Dimensions without coordinates: subject, batch
                                                                                                                        • team
                                                                                                                          (team)
                                                                                                                          <U1
                                                                                                                          'a' 'b' 'c' 'd' 'e' 'f'
                                                                                                                          array(['a', 'b', 'c', 'd', 'e', 'f'], dtype='<U1')
                                                                                                                        • chain
                                                                                                                          (chain)
                                                                                                                          int64
                                                                                                                          0 1 2 3
                                                                                                                          array([0, 1, 2, 3])
                                                                                                                        • draw
                                                                                                                          (draw)
                                                                                                                          int64
                                                                                                                          0 1 2 3 4 5 6 7 8 9
                                                                                                                          array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
                                                                                                                        • team
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Index(['a', 'b', 'c', 'd', 'e', 'f'], dtype='object', name='team'))
                                                                                                                        • chain
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3], dtype='int64', name='chain'))
                                                                                                                        • draw
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype='int64', name='draw'))
                                                                                                                        • " ], "text/plain": [ "\n", - "0.02322 0.252 1.428 0.06006 0.01792 ... 0.3755 -0.1818 0.1006 0.06794 1.643\n", + "0.2426 0.2904 0.6682 -0.1603 0.02198 ... -0.102 -0.08568 0.4546 0.2521 1.719\n", "Coordinates:\n", " * team (team)
                                                                                                                        • chain
                                                                                                                          (chain)
                                                                                                                          int64
                                                                                                                          0 1 2 3
                                                                                                                          array([0, 1, 2, 3])
                                                                                                                        • draw
                                                                                                                          (draw)
                                                                                                                          int64
                                                                                                                          0 1 2 3 4 5 6 7 8 9
                                                                                                                          array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
                                                                                                                        • team
                                                                                                                          (team)
                                                                                                                          <U1
                                                                                                                          'a' 'b' 'c' 'd' 'e' 'f'
                                                                                                                          array(['a', 'b', 'c', 'd', 'e', 'f'], dtype='<U1')
                                                                                                                        • chain
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3], dtype='int64', name='chain'))
                                                                                                                        • draw
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype='int64', name='draw'))
                                                                                                                        • team
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Index(['a', 'b', 'c', 'd', 'e', 'f'], dtype='object', name='team'))
                                                                                                                        • " ], "text/plain": [ "\n", @@ -1785,7 +1785,7 @@ " * quantile (quantile) float64 0.25 0.5 0.75\n", " * chain (chain) int64 0 1 2 3\n", " * draw (draw) int64 0 1 2 3 4 5 6 7 8 9\n", - " * team (team) <U1 'a' 'b' 'c' 'd' 'e' 'f'
                                                                                                                        • quantile
                                                                                                                          (quantile)
                                                                                                                          float64
                                                                                                                          0.25 0.5 0.75
                                                                                                                          array([0.25, 0.5 , 0.75])
                                                                                                                        • chain
                                                                                                                          (chain)
                                                                                                                          int64
                                                                                                                          0 1 2 3
                                                                                                                          array([0, 1, 2, 3])
                                                                                                                        • draw
                                                                                                                          (draw)
                                                                                                                          int64
                                                                                                                          0 1 2 3 4 5 6 7 8 9
                                                                                                                          array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
                                                                                                                        • team
                                                                                                                          (team)
                                                                                                                          <U1
                                                                                                                          'a' 'b' 'c' 'd' 'e' 'f'
                                                                                                                          array(['a', 'b', 'c', 'd', 'e', 'f'], dtype='<U1')
                                                                                                                        • quantile
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Float64Index([0.25, 0.5, 0.75], dtype='float64', name='quantile'))
                                                                                                                        • chain
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3], dtype='int64', name='chain'))
                                                                                                                        • draw
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype='int64', name='draw'))
                                                                                                                        • team
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Index(['a', 'b', 'c', 'd', 'e', 'f'], dtype='object', name='team'))
                                                                                                                        • " ], "text/plain": [ "\n", @@ -2224,7 +2224,7 @@ " * point (point) float64 -5.0 -4.796 -4.592 -4.388 ... 4.388 4.592 4.796 5.0\n", " * chain (chain) int64 0 1 2 3\n", " * draw (draw) int64 0 1 2 3 4 5 6 7 8 9\n", - " * team (team) <U1 'a' 'b' 'c' 'd' 'e' 'f'
                                                                                                                        • " ], "text/plain": [ "\n", @@ -2327,14 +2327,12 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ - "
                                                                                                                        " + "
                                                                                                                        " ] }, - "metadata": { - "needs_background": "light" - }, + "metadata": {}, "output_type": "display_data" } ], @@ -2739,14 +2737,14 @@ "0.1588 0.2123 0.5543 0.7826 0.1913 0.6035 ... 0.1269 0.712 0.3044 0.1936 0.1223\n", "Coordinates:\n", " * chain (chain) int64 0 1 2 3\n", - " * draw (draw) int64 0 1 2 3 4 5 6 7 8 9
                                                                                                                        • chain
                                                                                                                          (chain)
                                                                                                                          int64
                                                                                                                          0 1 2 3
                                                                                                                          array([0, 1, 2, 3])
                                                                                                                        • draw
                                                                                                                          (draw)
                                                                                                                          int64
                                                                                                                          0 1 2 3 4 5 6 7 8 9
                                                                                                                          array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
                                                                                                                        • chain
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3], dtype='int64', name='chain'))
                                                                                                                        • draw
                                                                                                                          PandasIndex
                                                                                                                          PandasIndex(Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype='int64', name='draw'))
                                                                                                                        • " ], "text/plain": [ "\n", @@ -3139,10 +3137,7 @@ "}\n", "
                                                                                                                        <xarray.DataArray 'score' (match: 12, chain: 4, draw: 10)>\n",
        "14 14 14 14 14 31 14 1 31 14 31 1 14 1 ... 15 15 15 15 15 1 34 15 15 1 34 34 34\n",
-       "Coordinates:\n",
-       "  * chain    (chain) int64 0 1 2 3\n",
-       "  * draw     (draw) int64 0 1 2 3 4 5 6 7 8 9\n",
-       "Dimensions without coordinates: match
                                                                                                                            • " ], "text/plain": [ "\n", "14 14 14 14 14 31 14 1 31 14 31 1 14 1 ... 15 15 15 15 15 1 34 15 15 1 34 34 34\n", - "Coordinates:\n", - " * chain (chain) int64 0 1 2 3\n", - " * draw (draw) int64 0 1 2 3 4 5 6 7 8 9\n", - "Dimensions without coordinates: match" + "Dimensions without coordinates: match, chain, draw" ] }, "execution_count": 11, @@ -3596,10 +3588,10 @@ "Data variables:\n", " score (match) float64 1.466 0.2149 0.6788 1.361 ... 1.099 1.156 1.265\n", " mu (team) float64 0.8152 1.84 2.102 1.806 1.091 0.9678\n", - " sigma float64 1.314
                                                                                                                            • team
                                                                                                                              PandasIndex
                                                                                                                              PandasIndex(Index(['a', 'b', 'c', 'd', 'e', 'f'], dtype='object', name='team'))
                                                                                                                            • " ], "text/plain": [ "\n", @@ -4000,7 +3992,7 @@ " x_plot float64 2.632\n", " mu float64 0.4878\n", " sigma float64 0.39\n", - " score float64 1.0" + " score float64 1.0" ], "text/plain": [ "\n", @@ -4031,18 +4023,18 @@ "name": "stdout", "output_type": "stream", "text": [ - "Last updated: Fri Dec 09 2022\n", + "Last updated: Mon Jan 16 2023\n", "\n", "Python implementation: CPython\n", - "Python version : 3.9.13\n", - "IPython version : 8.4.0\n", + "Python version : 3.10.8\n", + "IPython version : 8.7.0\n", "\n", - "xarray_einstats: 0.4.0\n", + "xarray_einstats: 0.5.0\n", "xarray : 2022.12.0\n", "\n", - "numpy : 1.23.5\n", - "scipy : 1.9.3\n", - "matplotlib: 3.5.3\n", + "numpy : 1.24.0\n", + "matplotlib: 3.6.2\n", + "scipy : 1.10.0\n", "\n", "Watermark: 2.3.1\n", "\n" @@ -4079,7 +4071,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.13" + "version": "3.10.8" } }, "nbformat": 4, diff --git a/src/xarray_einstats/__init__.py b/src/xarray_einstats/__init__.py index b47060a..e7017f5 100644 --- a/src/xarray_einstats/__init__.py +++ b/src/xarray_einstats/__init__.py @@ -9,7 +9,7 @@ __all__ = ["einsum", "raw_einsum", "einsum_path", "matmul", "zeros_ref", "ones_ref", "empty_ref"] -__version__ = "0.5.0.dev0" +__version__ = "0.5.0" def sort(da, dim, **kwargs):