de-dup threshold plot rows

Author: JohnMount

README.ipynb

@@ -18,47 +18,13 @@ tests/test_stats1.py .                                                   [ 87%]
 tests/test_threshold_stats.py .                                          [ 93%]
 tests/test_types_in_frame.py .                                           [100%]
 
-=============================== warnings summary ===============================
-tests/test_plots.py::test_graphs
-  /Users/johnmount/Documents/work/wvu/pkg/wvu/util.py:333: FutureWarning: 
-  
-  `shade` is now deprecated in favor of `fill`; setting `fill=True`.
-  This will become an error in seaborn v0.14.0; please update your code.
-  
-    seaborn.kdeplot(preds_on_positive, label=positive_label, shade=True)
-
-tests/test_plots.py::test_graphs
-  /Users/johnmount/Documents/work/wvu/pkg/wvu/util.py:334: FutureWarning: 
-  
-  `shade` is now deprecated in favor of `fill`; setting `fill=True`.
-  This will become an error in seaborn v0.14.0; please update your code.
-  
-    seaborn.kdeplot(preds_on_negative, label=negative_label, shade=True)
-
-tests/test_plots.py::test_graphs
-  /Users/johnmount/Documents/work/wvu/pkg/wvu/util.py:430: FutureWarning: 
-  
-  `shade` is now deprecated in favor of `fill`; setting `fill=True`.
-  This will become an error in seaborn v0.14.0; please update your code.
-  
-    seaborn.kdeplot(preds_on_positive, label=positive_label, shade=True)
-
-tests/test_plots.py::test_graphs
-  /Users/johnmount/Documents/work/wvu/pkg/wvu/util.py:431: FutureWarning: 
-  
-  `shade` is now deprecated in favor of `fill`; setting `fill=True`.
-  This will become an error in seaborn v0.14.0; please update your code.
-  
-    seaborn.kdeplot(preds_on_negative, label=negative_label, shade=True)
-
--- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
-
 ---------- coverage: platform darwin, python 3.9.15-final-0 ----------
 Name              Stmts   Miss  Cover
 -------------------------------------
-wvu/__init__.py       3      0   100%
-wvu/util.py         321      7    98%
+wvu/__init__.py       4      0   100%
+wvu/util.py         324      7    98%
 -------------------------------------
-TOTAL               324      7    98%
+TOTAL               328      7    98%
+
 
-======================== 16 passed, 4 warnings in 9.37s ========================
+============================= 16 passed in 10.38s ==============================

coverage.txt

@@ -4,3 +4,6 @@
 __doc__ = """
 This<https://github.com/WinVector/wvu> is a package of example files for teaching data science.
 """
+
+import wvu.util as util
+

pkg/build/lib/wvu/__init__.py

@@ -330,8 +330,8 @@ def dual_density_plot(
     preds_on_negative = [
         probs[i] for i in range(len(probs)) if not istrue[i] == truth_target
     ]
-    seaborn.kdeplot(preds_on_positive, label=positive_label, shade=True)
-    seaborn.kdeplot(preds_on_negative, label=negative_label, shade=True)
+    seaborn.kdeplot(preds_on_positive, label=positive_label, fill=True)
+    seaborn.kdeplot(preds_on_negative, label=negative_label, fill=True)
     matplotlib.pyplot.ylabel(ylabel)
     matplotlib.pyplot.xlabel(xlabel)
     matplotlib.pyplot.title(title)
@@ -427,8 +427,8 @@ def dual_density_plot_proba1(
     preds_on_negative = [
         probs[i, 1] for i in range(len(probs)) if not istrue[i] == truth_target
     ]
-    seaborn.kdeplot(preds_on_positive, label=positive_label, shade=True)
-    seaborn.kdeplot(preds_on_negative, label=negative_label, shade=True)
+    seaborn.kdeplot(preds_on_positive, label=positive_label, fill=True)
+    seaborn.kdeplot(preds_on_negative, label=negative_label, fill=True)
     matplotlib.pyplot.ylabel(ylabel)
     matplotlib.pyplot.xlabel(xlabel)
     matplotlib.pyplot.title(title)
@@ -722,7 +722,6 @@ def threshold_statistics(
     sorted_frame["notY"] = 1 - sorted_frame["truth"]  # falses
     sorted_frame["one"] = 1
     del sorted_frame["orig_index"]
-
     # pseudo-observation to get end-case (accept nothing case)
     eps = 1.0e-6
     sorted_frame = pandas.concat(
@@ -747,7 +746,6 @@ def threshold_statistics(
         ]
     )
     sorted_frame.reset_index(inplace=True, drop=True)
-
     # basic cumulative facts
     sorted_frame["count"] = sorted_frame["one"].cumsum()  # predicted true so far
     sorted_frame["fraction"] = sorted_frame["count"] / max(1, sorted_frame["one"].sum())
@@ -771,25 +769,28 @@ def threshold_statistics(
         + sorted_frame["notY"].sum()
         - sorted_frame["notY"].cumsum()  # true negative count
     ) / sorted_frame["one"].sum()
-
     # approximate cdf work
     sorted_frame["cdf"] = 1 - sorted_frame["fraction"]
-
     # derived facts and synonyms
     sorted_frame["recall"] = sorted_frame["true_positive_rate"]
     sorted_frame["sensitivity"] = sorted_frame["recall"]
     sorted_frame["specificity"] = 1 - sorted_frame["false_positive_rate"]
-
     # re-order for neatness
     sorted_frame["new_index"] = sorted_frame.index.copy()
     sorted_frame.sort_values(["new_index"], ascending=[False], inplace=True)
     sorted_frame.reset_index(inplace=True, drop=True)
-
     # clean up
     del sorted_frame["notY"]
     del sorted_frame["one"]
     del sorted_frame["new_index"]
     del sorted_frame["truth"]
+    # limit down to last version of each threshold
+    if sorted_frame.shape[0] > 1:
+        want_row = [True] + list(
+            numpy.array(sorted_frame["threshold"][range(sorted_frame.shape[0]-1)]) 
+                != numpy.array(sorted_frame["threshold"][range(1, sorted_frame.shape[0])])
+        )
+        sorted_frame = sorted_frame.loc[want_row, :].reset_index(drop=True, inplace=False)
     return sorted_frame
 
 
@@ -874,7 +875,9 @@ def threshold_plot(
                 pandas.DataFrame({"measure": plotvars, "value": plotvars}),
                 control_table_keys=["measure"],
                 record_keys=["threshold"],
-            )
+                strict=False,
+            ),
+            strict=False,
         )
         prtlong = reshaper.transform(to_plot)
         grid = seaborn.FacetGrid(

pkg/build/lib/wvu/util.py

@@ -58,6 +58,8 @@ <h1 class="modulename">
 </span><span id="L-4"><a href="#L-4"><span class="linenos">4</span></a><span class="vm">__doc__</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;</span>
 </span><span id="L-5"><a href="#L-5"><span class="linenos">5</span></a><span class="s2">This&lt;https://github.com/WinVector/wvu&gt; is a package of example files for teaching data science.</span>
 </span><span id="L-6"><a href="#L-6"><span class="linenos">6</span></a><span class="s2">&quot;&quot;&quot;</span>
+</span><span id="L-7"><a href="#L-7"><span class="linenos">7</span></a>
+</span><span id="L-8"><a href="#L-8"><span class="linenos">8</span></a><span class="kn">import</span> <span class="nn">wvu.util</span> <span class="k">as</span> <span class="nn">util</span>
 </span></pre></div>