Small changes. Iris dataset. New unitests

Author: cyberosa

dabest/plot_tools.py

@@ -44,6 +44,9 @@ def get_swarm_spans(coll):
     Given a matplotlib Collection, will obtain the x and y spans
     for the collection. Will return None if this fails.
     """
+    if coll is None:
+        raise ValueError("The collection `coll` parameter cannot be None")
+
     x, y = np.array(coll.get_offsets()).T
     try:
         return x.min(), x.max(), y.min(), y.max()
@@ -233,7 +236,6 @@ def normalize_dict(nested_dict, target):
     for key, value in nested_dict.items():
         if isinstance(value, dict):
             for subkey in value.keys():
-                # value[subkey] = target[subkey]['right']
                 if subkey in val.keys():
                     if val[subkey] != 0:
                         # Address the problem when one of the label have zero value
@@ -248,6 +250,12 @@ def normalize_dict(nested_dict, target):
 
 
 def width_determine(labels, data, pos="left"):
+    if labels is None:
+        raise ValueError("The `labels` parameter cannot be None")
+
+    if data is None:
+        raise ValueError("The `data` parameter cannot be None")
+    
     widths_norm = defaultdict()
     for i, label in enumerate(labels):
         myD = {}
@@ -513,16 +521,12 @@ def single_sankey(
     if sankey and strip_on:
         for leftLabel, rightLabel in itertools.product(leftLabels, rightLabels):
             labelColor = leftLabel
+            
             if rightColor:
                 labelColor = rightLabel
-            if (
-                len(
-                    dataFrame[
-                        (dataFrame.left == leftLabel) & (dataFrame.right == rightLabel)
-                    ]
-                )
-                > 0
-            ):
+            
+            if len(dataFrame[(dataFrame.left == leftLabel) & 
+                        (dataFrame.right == rightLabel)]) > 0:
                 # Create array of y values for each strip, half at left value,
                 # half at right, convolve
                 ys_d = np.array(
@@ -531,18 +535,11 @@ def single_sankey(
                 )
                 ys_d = np.convolve(ys_d, 0.05 * np.ones(20), mode="valid")
                 ys_d = np.convolve(ys_d, 0.05 * np.ones(20), mode="valid")
-                ys_u = np.array(
-                    50
-                    * [
-                        leftWidths_norm[leftLabel]["bottom"]
-                        + ns_l_norm[leftLabel][rightLabel]
-                    ]
-                    + 50
-                    * [
-                        rightWidths_norm[rightLabel]["bottom"]
-                        + ns_r_norm[leftLabel][rightLabel]
-                    ]
-                )
+                # to remove the array wrapping behaviour of black
+                # fmt: off
+                ys_u = np.array(50 * [leftWidths_norm[leftLabel]['bottom'] + ns_l_norm[leftLabel][rightLabel]] + \
+                    50 * [rightWidths_norm[rightLabel]['bottom'] + ns_r_norm[leftLabel][rightLabel]])
+                # fmt: on
                 ys_u = np.convolve(ys_u, 0.05 * np.ones(20), mode="valid")
                 ys_u = np.convolve(ys_u, 0.05 * np.ones(20), mode="valid")
 

nbs/API/bootstrap.ipynb

@@ -18,7 +18,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | default_exp _bootstrap_tools"
+    "#| default_exp _bootstrap_tools"
    ]
   },
   {
@@ -28,7 +28,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | hide\n",
+    "#| hide\n",
     "from __future__ import division\n",
     "from nbdev.showdoc import *\n",
     "import nbdev\n",
@@ -43,7 +43,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# |export\n",
+    "#| export\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "import seaborn as sns\n",
@@ -60,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# |export\n",
+    "#| export\n",
     "class bootstrap:\n",
     "    \"\"\"\n",
     "    Computes the summary statistic and a bootstrapped confidence interval.\n",
@@ -274,7 +274,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# |export\n",
+    "#| export\n",
     "def jackknife_indexes(data):\n",
     "    # Taken without modification from scikits.bootstrap package.\n",
     "    \"\"\"\n",

nbs/API/confint_1group.ipynb

@@ -53,7 +53,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#|export\n",
+    "#| export\n",
     "import numpy as np\n",
     "from numpy.random import PCG64, RandomState\n",
     "from scipy.stats import norm\n",

nbs/API/plot_tools.ipynb

@@ -99,6 +99,9 @@
     "    Given a matplotlib Collection, will obtain the x and y spans\n",
     "    for the collection. Will return None if this fails.\n",
     "    \"\"\"\n",
+    "    if coll is None:\n",
+    "        raise ValueError(\"The collection `coll` parameter cannot be None\")\n",
+    "\n",
     "    x, y = np.array(coll.get_offsets()).T\n",
     "    try:\n",
     "        return x.min(), x.max(), y.min(), y.max()\n",
@@ -288,7 +291,6 @@
     "    for key, value in nested_dict.items():\n",
     "        if isinstance(value, dict):\n",
     "            for subkey in value.keys():\n",
-    "                # value[subkey] = target[subkey]['right']\n",
     "                if subkey in val.keys():\n",
     "                    if val[subkey] != 0:\n",
     "                        # Address the problem when one of the label have zero value\n",
@@ -303,6 +305,12 @@
     "\n",
     "\n",
     "def width_determine(labels, data, pos=\"left\"):\n",
+    "    if labels is None:\n",
+    "        raise ValueError(\"The `labels` parameter cannot be None\")\n",
+    "\n",
+    "    if data is None:\n",
+    "        raise ValueError(\"The `data` parameter cannot be None\")\n",
+    "    \n",
     "    widths_norm = defaultdict()\n",
     "    for i, label in enumerate(labels):\n",
     "        myD = {}\n",
@@ -568,16 +576,12 @@
     "    if sankey and strip_on:\n",
     "        for leftLabel, rightLabel in itertools.product(leftLabels, rightLabels):\n",
     "            labelColor = leftLabel\n",
+    "            \n",
     "            if rightColor:\n",
     "                labelColor = rightLabel\n",
-    "            if (\n",
-    "                len(\n",
-    "                    dataFrame[\n",
-    "                        (dataFrame.left == leftLabel) & (dataFrame.right == rightLabel)\n",
-    "                    ]\n",
-    "                )\n",
-    "                > 0\n",
-    "            ):\n",
+    "            \n",
+    "            if len(dataFrame[(dataFrame.left == leftLabel) & \n",
+    "                        (dataFrame.right == rightLabel)]) > 0:\n",
     "                # Create array of y values for each strip, half at left value,\n",
     "                # half at right, convolve\n",
     "                ys_d = np.array(\n",
@@ -586,18 +590,11 @@
     "                )\n",
     "                ys_d = np.convolve(ys_d, 0.05 * np.ones(20), mode=\"valid\")\n",
     "                ys_d = np.convolve(ys_d, 0.05 * np.ones(20), mode=\"valid\")\n",
-    "                ys_u = np.array(\n",
-    "                    50\n",
-    "                    * [\n",
-    "                        leftWidths_norm[leftLabel][\"bottom\"]\n",
-    "                        + ns_l_norm[leftLabel][rightLabel]\n",
-    "                    ]\n",
-    "                    + 50\n",
-    "                    * [\n",
-    "                        rightWidths_norm[rightLabel][\"bottom\"]\n",
-    "                        + ns_r_norm[leftLabel][rightLabel]\n",
-    "                    ]\n",
-    "                )\n",
+    "                # to remove the array wrapping behaviour of black\n",
+    "                # fmt: off\n",
+    "                ys_u = np.array(50 * [leftWidths_norm[leftLabel]['bottom'] + ns_l_norm[leftLabel][rightLabel]] + \\\n",
+    "                    50 * [rightWidths_norm[rightLabel]['bottom'] + ns_r_norm[leftLabel][rightLabel]])\n",
+    "                # fmt: on\n",
     "                ys_u = np.convolve(ys_u, 0.05 * np.ones(20), mode=\"valid\")\n",
     "                ys_u = np.convolve(ys_u, 0.05 * np.ones(20), mode=\"valid\")\n",
     "\n",

nbs/tests/data/iris.csv

@@ -0,0 +1,151 @@
+sepal_length,sepal_width,petal_length,petal_width,species
+5.1,3.5,1.4,0.2,setosa
+4.9,3.0,1.4,0.2,setosa
+4.7,3.2,1.3,0.2,setosa
+4.6,3.1,1.5,0.2,setosa
+5.0,3.6,1.4,0.2,setosa
+5.4,3.9,1.7,0.4,setosa
+4.6,3.4,1.4,0.3,setosa
+5.0,3.4,1.5,0.2,setosa
+4.4,2.9,1.4,0.2,setosa
+4.9,3.1,1.5,0.1,setosa
+5.4,3.7,1.5,0.2,setosa
+4.8,3.4,1.6,0.2,setosa
+4.8,3.0,1.4,0.1,setosa
+4.3,3.0,1.1,0.1,setosa
+5.8,4.0,1.2,0.2,setosa
+5.7,4.4,1.5,0.4,setosa
+5.4,3.9,1.3,0.4,setosa
+5.1,3.5,1.4,0.3,setosa
+5.7,3.8,1.7,0.3,setosa
+5.1,3.8,1.5,0.3,setosa
+5.4,3.4,1.7,0.2,setosa
+5.1,3.7,1.5,0.4,setosa
+4.6,3.6,1.0,0.2,setosa
+5.1,3.3,1.7,0.5,setosa
+4.8,3.4,1.9,0.2,setosa
+5.0,3.0,1.6,0.2,setosa
+5.0,3.4,1.6,0.4,setosa
+5.2,3.5,1.5,0.2,setosa
+5.2,3.4,1.4,0.2,setosa
+4.7,3.2,1.6,0.2,setosa
+4.8,3.1,1.6,0.2,setosa
+5.4,3.4,1.5,0.4,setosa
+5.2,4.1,1.5,0.1,setosa
+5.5,4.2,1.4,0.2,setosa
+4.9,3.1,1.5,0.2,setosa
+5.0,3.2,1.2,0.2,setosa
+5.5,3.5,1.3,0.2,setosa
+4.9,3.6,1.4,0.1,setosa
+4.4,3.0,1.3,0.2,setosa
+5.1,3.4,1.5,0.2,setosa
+5.0,3.5,1.3,0.3,setosa
+4.5,2.3,1.3,0.3,setosa
+4.4,3.2,1.3,0.2,setosa
+5.0,3.5,1.6,0.6,setosa
+5.1,3.8,1.9,0.4,setosa
+4.8,3.0,1.4,0.3,setosa
+5.1,3.8,1.6,0.2,setosa
+4.6,3.2,1.4,0.2,setosa
+5.3,3.7,1.5,0.2,setosa
+5.0,3.3,1.4,0.2,setosa
+7.0,3.2,4.7,1.4,versicolor
+6.4,3.2,4.5,1.5,versicolor
+6.9,3.1,4.9,1.5,versicolor
+5.5,2.3,4.0,1.3,versicolor
+6.5,2.8,4.6,1.5,versicolor
+5.7,2.8,4.5,1.3,versicolor
+6.3,3.3,4.7,1.6,versicolor
+4.9,2.4,3.3,1.0,versicolor
+6.6,2.9,4.6,1.3,versicolor
+5.2,2.7,3.9,1.4,versicolor
+5.0,2.0,3.5,1.0,versicolor
+5.9,3.0,4.2,1.5,versicolor
+6.0,2.2,4.0,1.0,versicolor
+6.1,2.9,4.7,1.4,versicolor
+5.6,2.9,3.6,1.3,versicolor
+6.7,3.1,4.4,1.4,versicolor
+5.6,3.0,4.5,1.5,versicolor
+5.8,2.7,4.1,1.0,versicolor
+6.2,2.2,4.5,1.5,versicolor
+5.6,2.5,3.9,1.1,versicolor
+5.9,3.2,4.8,1.8,versicolor
+6.1,2.8,4.0,1.3,versicolor
+6.3,2.5,4.9,1.5,versicolor
+6.1,2.8,4.7,1.2,versicolor
+6.4,2.9,4.3,1.3,versicolor
+6.6,3.0,4.4,1.4,versicolor
+6.8,2.8,4.8,1.4,versicolor
+6.7,3.0,5.0,1.7,versicolor
+6.0,2.9,4.5,1.5,versicolor
+5.7,2.6,3.5,1.0,versicolor
+5.5,2.4,3.8,1.1,versicolor
+5.5,2.4,3.7,1.0,versicolor
+5.8,2.7,3.9,1.2,versicolor
+6.0,2.7,5.1,1.6,versicolor
+5.4,3.0,4.5,1.5,versicolor
+6.0,3.4,4.5,1.6,versicolor
+6.7,3.1,4.7,1.5,versicolor
+6.3,2.3,4.4,1.3,versicolor
+5.6,3.0,4.1,1.3,versicolor
+5.5,2.5,4.0,1.3,versicolor
+5.5,2.6,4.4,1.2,versicolor
+6.1,3.0,4.6,1.4,versicolor
+5.8,2.6,4.0,1.2,versicolor
+5.0,2.3,3.3,1.0,versicolor
+5.6,2.7,4.2,1.3,versicolor
+5.7,3.0,4.2,1.2,versicolor
+5.7,2.9,4.2,1.3,versicolor
+6.2,2.9,4.3,1.3,versicolor
+5.1,2.5,3.0,1.1,versicolor
+5.7,2.8,4.1,1.3,versicolor
+6.3,3.3,6.0,2.5,virginica
+5.8,2.7,5.1,1.9,virginica
+7.1,3.0,5.9,2.1,virginica
+6.3,2.9,5.6,1.8,virginica
+6.5,3.0,5.8,2.2,virginica
+7.6,3.0,6.6,2.1,virginica
+4.9,2.5,4.5,1.7,virginica
+7.3,2.9,6.3,1.8,virginica
+6.7,2.5,5.8,1.8,virginica
+7.2,3.6,6.1,2.5,virginica
+6.5,3.2,5.1,2.0,virginica
+6.4,2.7,5.3,1.9,virginica
+6.8,3.0,5.5,2.1,virginica
+5.7,2.5,5.0,2.0,virginica
+5.8,2.8,5.1,2.4,virginica
+6.4,3.2,5.3,2.3,virginica
+6.5,3.0,5.5,1.8,virginica
+7.7,3.8,6.7,2.2,virginica
+7.7,2.6,6.9,2.3,virginica
+6.0,2.2,5.0,1.5,virginica
+6.9,3.2,5.7,2.3,virginica
+5.6,2.8,4.9,2.0,virginica
+7.7,2.8,6.7,2.0,virginica
+6.3,2.7,4.9,1.8,virginica
+6.7,3.3,5.7,2.1,virginica
+7.2,3.2,6.0,1.8,virginica
+6.2,2.8,4.8,1.8,virginica
+6.1,3.0,4.9,1.8,virginica
+6.4,2.8,5.6,2.1,virginica
+7.2,3.0,5.8,1.6,virginica
+7.4,2.8,6.1,1.9,virginica
+7.9,3.8,6.4,2.0,virginica
+6.4,2.8,5.6,2.2,virginica
+6.3,2.8,5.1,1.5,virginica
+6.1,2.6,5.6,1.4,virginica
+7.7,3.0,6.1,2.3,virginica
+6.3,3.4,5.6,2.4,virginica
+6.4,3.1,5.5,1.8,virginica
+6.0,3.0,4.8,1.8,virginica
+6.9,3.1,5.4,2.1,virginica
+6.7,3.1,5.6,2.4,virginica
+6.9,3.1,5.1,2.3,virginica
+5.8,2.7,5.1,1.9,virginica
+6.8,3.2,5.9,2.3,virginica
+6.7,3.3,5.7,2.5,virginica
+6.7,3.0,5.2,2.3,virginica
+6.3,2.5,5.0,1.9,virginica
+6.5,3.0,5.2,2.0,virginica
+6.2,3.4,5.4,2.3,virginica
+5.9,3.0,5.1,1.8,virginica

nbs/tests/test_99_confidence_intervals.ipynb

@@ -213,10 +213,6 @@
    "display_name": "python3",
    "language": "python",
    "name": "python3"
-  },
-  "language_info": {
-   "name": "python",
-   "version": "3.10.12"
   }
  },
  "nbformat": 4,

nbs/tests/test_plot_tools.py

@@ -0,0 +1,25 @@
+import pytest
+from dabest.plot_tools import get_swarm_spans, width_determine
+import numpy as np
+
+
+def test_get_swarm_spans_wrong_parameters():
+    error_msg = "The collection `coll` parameter cannot be None"
+    with pytest.raises(ValueError) as excinfo:
+        get_swarm_spans(None)
+
+    assert error_msg in str(excinfo.value)
+
+
+def test_width_determine():
+    error_msg = "The `labels` parameter cannot be None"
+    with pytest.raises(ValueError) as excinfo:
+        width_determine(None, [])
+
+    assert error_msg in str(excinfo.value)
+
+    error_msg = "The `data` parameter cannot be None"
+    with pytest.raises(ValueError) as excinfo:
+        width_determine("some_labels", None)
+
+    assert error_msg in str(excinfo.value)