clean up types a bit

Author: JohnMount

coverage.txt

@@ -20,9 +20,9 @@ tests/test_threshold_stats.py .                                          [100%]
 Name               Stmts   Miss  Cover
 --------------------------------------
 wvpy/__init__.py       3      0   100%
-wvpy/util.py         307      7    98%
+wvpy/util.py         309      7    98%
 --------------------------------------
-TOTAL                310      7    98%
+TOTAL                312      7    98%
 
 
-============================== 14 passed in 7.22s ==============================
+============================== 14 passed in 6.89s ==============================

pkg/build/lib/wvpy/util.py

@@ -2,7 +2,7 @@
 Utility functions for teaching data science.
 """
 
-from typing import Iterable, Tuple
+from typing import Iterable, List, Tuple
 
 import re
 import numpy
@@ -16,7 +16,7 @@
 import itertools
 import pandas
 import math
-from data_algebra.cdata import *
+from data_algebra.cdata import RecordMap, RecordSpecification
 
 
 # noinspection PyPep8Naming
@@ -146,8 +146,8 @@ def matching_roc_area_curve(auc: float) -> dict:
     step = 0.01
     eval_pts = numpy.arange(0, 1 + step, step)
     q_eps = 1e-6
-    q_low = 0
-    q_high = 1
+    q_low = 0.0
+    q_high = 1.0
     while q_low + q_eps < q_high:
         q_mid = (q_low + q_high) / 2.0
         q_mid_area = numpy.mean(1 - (1 - (1 - eval_pts) ** q_mid) ** (1 / q_mid))
@@ -778,8 +778,8 @@ def threshold_plot(
     pred_var: str,
     truth_var: str,
     truth_target: bool = True,
-    threshold_range: Tuple[float, float] = (-math.inf, math.inf),
-    plotvars: Tuple = ("precision", "recall"),
+    threshold_range: Iterable[float] = (-math.inf, math.inf),
+    plotvars: Iterable[str] = ("precision", "recall"),
     title: str = "Measures as a function of threshold",
     *,
     show: bool = True,
@@ -820,10 +820,12 @@ def threshold_plot(
     if isinstance(plotvars, str):
         plotvars = [plotvars]
     else:
-        plotvars = [v for v in plotvars]
+        plotvars = list(plotvars)
     assert isinstance(plotvars, list)
     assert len(plotvars) > 0
     assert all([isinstance(v, str) for v in plotvars])
+    threshold_range = list(threshold_range)
+    assert len(threshold_range) == 2
     frame = d[[pred_var, truth_var]].copy()
     frame.reset_index(inplace=True, drop=True)
     frame["outcol"] = frame[truth_var] == truth_target

pkg/dist/wvpy-0.2.9-py3-none-any.whl

@@ -118,7 +118,7 @@ <h1 class="modulename">
 <span class="sd">Utility functions for teaching data science.</span>
 <span class="sd">&quot;&quot;&quot;</span>
 
-<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterable</span><span class="p">,</span> <span class="n">Tuple</span>
+<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterable</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Tuple</span>
 
 <span class="kn">import</span> <span class="nn">re</span>
 <span class="kn">import</span> <span class="nn">numpy</span>
@@ -132,7 +132,7 @@ <h1 class="modulename">
 <span class="kn">import</span> <span class="nn">itertools</span>
 <span class="kn">import</span> <span class="nn">pandas</span>
 <span class="kn">import</span> <span class="nn">math</span>
-<span class="kn">from</span> <span class="nn">data_algebra.cdata</span> <span class="kn">import</span> <span class="o">*</span>
+<span class="kn">from</span> <span class="nn">data_algebra.cdata</span> <span class="kn">import</span> <span class="n">RecordMap</span><span class="p">,</span> <span class="n">RecordSpecification</span>
 
 
 <span class="c1"># noinspection PyPep8Naming</span>
@@ -262,8 +262,8 @@ <h1 class="modulename">
     <span class="n">step</span> <span class="o">=</span> <span class="mf">0.01</span>
     <span class="n">eval_pts</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span> <span class="o">+</span> <span class="n">step</span><span class="p">,</span> <span class="n">step</span><span class="p">)</span>
     <span class="n">q_eps</span> <span class="o">=</span> <span class="mf">1e-6</span>
-    <span class="n">q_low</span> <span class="o">=</span> <span class="mi">0</span>
-    <span class="n">q_high</span> <span class="o">=</span> <span class="mi">1</span>
+    <span class="n">q_low</span> <span class="o">=</span> <span class="mf">0.0</span>
+    <span class="n">q_high</span> <span class="o">=</span> <span class="mf">1.0</span>
     <span class="k">while</span> <span class="n">q_low</span> <span class="o">+</span> <span class="n">q_eps</span> <span class="o">&lt;</span> <span class="n">q_high</span><span class="p">:</span>
         <span class="n">q_mid</span> <span class="o">=</span> <span class="p">(</span><span class="n">q_low</span> <span class="o">+</span> <span class="n">q_high</span><span class="p">)</span> <span class="o">/</span> <span class="mf">2.0</span>
         <span class="n">q_mid_area</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">eval_pts</span><span class="p">)</span> <span class="o">**</span> <span class="n">q_mid</span><span class="p">)</span> <span class="o">**</span> <span class="p">(</span><span class="mi">1</span> <span class="o">/</span> <span class="n">q_mid</span><span class="p">))</span>
@@ -894,8 +894,8 @@ <h1 class="modulename">
     <span class="n">pred_var</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">truth_var</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">truth_target</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
-    <span class="n">threshold_range</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="o">-</span><span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">,</span> <span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">),</span>
-    <span class="n">plotvars</span><span class="p">:</span> <span class="n">Tuple</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;precision&quot;</span><span class="p">,</span> <span class="s2">&quot;recall&quot;</span><span class="p">),</span>
+    <span class="n">threshold_range</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="o">-</span><span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">,</span> <span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">),</span>
+    <span class="n">plotvars</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;precision&quot;</span><span class="p">,</span> <span class="s2">&quot;recall&quot;</span><span class="p">),</span>
     <span class="n">title</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;Measures as a function of threshold&quot;</span><span class="p">,</span>
     <span class="o">*</span><span class="p">,</span>
     <span class="n">show</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
@@ -936,10 +936,12 @@ <h1 class="modulename">
     <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">plotvars</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
         <span class="n">plotvars</span> <span class="o">=</span> <span class="p">[</span><span class="n">plotvars</span><span class="p">]</span>
     <span class="k">else</span><span class="p">:</span>
-        <span class="n">plotvars</span> <span class="o">=</span> <span class="p">[</span><span class="n">v</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">plotvars</span><span class="p">]</span>
+        <span class="n">plotvars</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">plotvars</span><span class="p">)</span>
     <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">plotvars</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span>
     <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">plotvars</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span>
     <span class="k">assert</span> <span class="nb">all</span><span class="p">([</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">plotvars</span><span class="p">])</span>
+    <span class="n">threshold_range</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">threshold_range</span><span class="p">)</span>
+    <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">threshold_range</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span>
     <span class="n">frame</span> <span class="o">=</span> <span class="n">d</span><span class="p">[[</span><span class="n">pred_var</span><span class="p">,</span> <span class="n">truth_var</span><span class="p">]]</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
     <span class="n">frame</span><span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
     <span class="n">frame</span><span class="p">[</span><span class="s2">&quot;outcol&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">frame</span><span class="p">[</span><span class="n">truth_var</span><span class="p">]</span> <span class="o">==</span> <span class="n">truth_target</span>
@@ -1317,8 +1319,8 @@ <h1 class="modulename">
     <span class="n">step</span> <span class="o">=</span> <span class="mf">0.01</span>
     <span class="n">eval_pts</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span> <span class="o">+</span> <span class="n">step</span><span class="p">,</span> <span class="n">step</span><span class="p">)</span>
     <span class="n">q_eps</span> <span class="o">=</span> <span class="mf">1e-6</span>
-    <span class="n">q_low</span> <span class="o">=</span> <span class="mi">0</span>
-    <span class="n">q_high</span> <span class="o">=</span> <span class="mi">1</span>
+    <span class="n">q_low</span> <span class="o">=</span> <span class="mf">0.0</span>
+    <span class="n">q_high</span> <span class="o">=</span> <span class="mf">1.0</span>
     <span class="k">while</span> <span class="n">q_low</span> <span class="o">+</span> <span class="n">q_eps</span> <span class="o">&lt;</span> <span class="n">q_high</span><span class="p">:</span>
         <span class="n">q_mid</span> <span class="o">=</span> <span class="p">(</span><span class="n">q_low</span> <span class="o">+</span> <span class="n">q_high</span><span class="p">)</span> <span class="o">/</span> <span class="mf">2.0</span>
         <span class="n">q_mid_area</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">eval_pts</span><span class="p">)</span> <span class="o">**</span> <span class="n">q_mid</span><span class="p">)</span> <span class="o">**</span> <span class="p">(</span><span class="mi">1</span> <span class="o">/</span> <span class="n">q_mid</span><span class="p">))</span>
@@ -2420,8 +2422,8 @@ <h1 class="modulename">
     pred_var: str,
     truth_var: str,
     truth_target: bool = True,
-    threshold_range: Tuple[float, float] = (-inf, inf),
-    plotvars: Tuple = (&#39;precision&#39;, &#39;recall&#39;),
+    threshold_range: Iterable[float] = (-inf, inf),
+    plotvars: Iterable[str] = (&#39;precision&#39;, &#39;recall&#39;),
     title: str = &#39;Measures as a function of threshold&#39;,
     *,
     show: bool = True
@@ -2435,8 +2437,8 @@ <h1 class="modulename">
     <span class="n">pred_var</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">truth_var</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">truth_target</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
-    <span class="n">threshold_range</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="o">-</span><span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">,</span> <span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">),</span>
-    <span class="n">plotvars</span><span class="p">:</span> <span class="n">Tuple</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;precision&quot;</span><span class="p">,</span> <span class="s2">&quot;recall&quot;</span><span class="p">),</span>
+    <span class="n">threshold_range</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="o">-</span><span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">,</span> <span class="n">math</span><span class="o">.</span><span class="n">inf</span><span class="p">),</span>
+    <span class="n">plotvars</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;precision&quot;</span><span class="p">,</span> <span class="s2">&quot;recall&quot;</span><span class="p">),</span>
     <span class="n">title</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;Measures as a function of threshold&quot;</span><span class="p">,</span>
     <span class="o">*</span><span class="p">,</span>
     <span class="n">show</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
@@ -2477,10 +2479,12 @@ <h1 class="modulename">
     <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">plotvars</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
         <span class="n">plotvars</span> <span class="o">=</span> <span class="p">[</span><span class="n">plotvars</span><span class="p">]</span>
     <span class="k">else</span><span class="p">:</span>
-        <span class="n">plotvars</span> <span class="o">=</span> <span class="p">[</span><span class="n">v</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">plotvars</span><span class="p">]</span>
+        <span class="n">plotvars</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">plotvars</span><span class="p">)</span>
     <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">plotvars</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span>
     <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">plotvars</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span>
     <span class="k">assert</span> <span class="nb">all</span><span class="p">([</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">plotvars</span><span class="p">])</span>
+    <span class="n">threshold_range</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">threshold_range</span><span class="p">)</span>
+    <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">threshold_range</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span>
     <span class="n">frame</span> <span class="o">=</span> <span class="n">d</span><span class="p">[[</span><span class="n">pred_var</span><span class="p">,</span> <span class="n">truth_var</span><span class="p">]]</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
     <span class="n">frame</span><span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
     <span class="n">frame</span><span class="p">[</span><span class="s2">&quot;outcol&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">frame</span><span class="p">[</span><span class="n">truth_var</span><span class="p">]</span> <span class="o">==</span> <span class="n">truth_target</span>