test user coder path

coverage.txt

@@ -2,32 +2,33 @@
 platform darwin -- Python 3.7.5, pytest-5.2.4, py-1.8.0, pluggy-0.13.0
 rootdir: /Users/johnmount/Documents/work/pyvtreat/pkg
 plugins: cov-2.8.1
-collected 15 items
+collected 16 items
 
-pkg/tests/test_classification.py ..                                      [ 13%]
-pkg/tests/test_col_name_issues.py ...                                    [ 33%]
-pkg/tests/test_imputation_controls.py .                                  [ 40%]
-pkg/tests/test_multinomial.py .                                          [ 46%]
-pkg/tests/test_nan_inf.py .                                              [ 53%]
-pkg/tests/test_outcome_name_required.py .                                [ 60%]
-pkg/tests/test_perm_cor.py .                                             [ 66%]
-pkg/tests/test_r1_issue.py .                                             [ 73%]
-pkg/tests/test_range.py .                                                [ 80%]
-pkg/tests/test_regression.py .                                           [ 86%]
-pkg/tests/test_unsupervised.py .                                         [ 93%]
+pkg/tests/test_classification.py ..                                      [ 12%]
+pkg/tests/test_col_name_issues.py ...                                    [ 31%]
+pkg/tests/test_imputation_controls.py .                                  [ 37%]
+pkg/tests/test_multinomial.py .                                          [ 43%]
+pkg/tests/test_nan_inf.py .                                              [ 50%]
+pkg/tests/test_outcome_name_required.py .                                [ 56%]
+pkg/tests/test_perm_cor.py .                                             [ 62%]
+pkg/tests/test_r1_issue.py .                                             [ 68%]
+pkg/tests/test_range.py .                                                [ 75%]
+pkg/tests/test_regression.py .                                           [ 81%]
+pkg/tests/test_unsupervised.py .                                         [ 87%]
+pkg/tests/test_user_coders.py .                                          [ 93%]
 pkg/tests/test_util.py .                                                 [100%]
 
 ---------- coverage: platform darwin, python 3.7.5-final-0 -----------
 Name                        Stmts   Miss  Cover
 -----------------------------------------------
 pkg/vtreat/__init__.py          6      0   100%
 pkg/vtreat/cross_plan.py      104     57    45%
-pkg/vtreat/transform.py        17     10    41%
+pkg/vtreat/transform.py        17      4    76%
 pkg/vtreat/util.py            161     25    84%
-pkg/vtreat/vtreat_api.py      218     43    80%
-pkg/vtreat/vtreat_impl.py     575    107    81%
+pkg/vtreat/vtreat_api.py      218     42    81%
+pkg/vtreat/vtreat_impl.py     575     79    86%
 -----------------------------------------------
-TOTAL                        1081    242    78%
+TOTAL                        1081    207    81%
 
 
-============================== 15 passed in 9.39s ==============================
+============================= 16 passed in 10.34s ==============================

pkg/tests/test_user_coders.py

@@ -0,0 +1,140 @@
+
+# From:
+# https://github.com/WinVector/pyvtreat/blob/master/Examples/UserCoders/UserCoders.ipynb
+
+
+import pandas
+import numpy
+import numpy.random
+# import seaborn
+
+import vtreat
+import vtreat.util
+import vtreat.transform
+
+have_sklearn = True
+try:
+    import sklearn.linear_model
+    import sklearn
+except Exception:
+    have_sklean = False
+
+
+def test_user_coders():
+    sklearn.warnings.filterwarnings('ignore')
+
+    # avoid depending on sklearn.metrics.r2_score
+    def r_squared(*, y_true, y_pred):
+        y_true = numpy.asarray(y_true)
+        y_pred = numpy.asarray(y_pred)
+        return 1 - numpy.sum((y_true - y_pred)**2)/numpy.sum((y_true - numpy.mean(y_true))**2)
+
+    # %%
+
+    class PolyTransform(vtreat.transform.UserTransform):
+        """a polynomial model"""
+
+        def __init__(self, *, deg=5, alpha=0.1):
+            vtreat.transform.UserTransform.__init__(self, treatment='poly')
+            self.models_ = None
+            self.deg = deg
+            self.alpha = alpha
+
+        def poly_terms(self, vname, vec):
+            vec = numpy.asarray(vec)
+            r = pandas.DataFrame({'x': vec})
+            for d in range(1, self.deg + 1):
+                r[vname + '_' + str(d)] = vec ** d
+            return r
+
+        def fit(self, X, y):
+            self.models_ = {}
+            self.incoming_vars_ = []
+            self.derived_vars_ = []
+            for v in X.columns:
+                if vtreat.util.can_convert_v_to_numeric(X[v]):
+                    X_v = self.poly_terms(v, X[v])
+                    model_v = sklearn.linear_model.Ridge(alpha=self.alpha).fit(X_v, y)
+                    new_var = v + "_poly"
+                    self.models_[v] = (model_v, [c for c in X_v.columns], new_var)
+                    self.incoming_vars_.append(v)
+                    self.derived_vars_.append(new_var)
+            return self
+
+        def transform(self, X):
+            r = pandas.DataFrame()
+            for k, v in self.models_.items():
+                model_k = v[0]
+                cols_k = v[1]
+                new_var = v[2]
+                X_k = self.poly_terms(k, X[k])
+                xform_k = model_k.predict(X_k)
+                r[new_var] = xform_k
+            return r
+
+    # %%
+
+    d = pandas.DataFrame({'x': [i for i in range(100)]})
+    d['y'] = numpy.sin(0.2 * d['x']) + 0.2 * numpy.random.normal(size=d.shape[0])
+    d.head()
+
+    # %%
+
+    step = PolyTransform(deg=10)
+
+    # %%
+
+    fit = step.fit_transform(d[['x']], d['y'])
+    fit['x'] = d['x']
+    fit.head()
+
+    # %%
+
+    # seaborn.scatterplot(x='x', y='y', data=d)
+    # seaborn.lineplot(x='x', y='x_poly', data=fit, color='red', alpha=0.5)
+
+    # %%
+
+    transform = vtreat.NumericOutcomeTreatment(
+        outcome_name='y',
+        params=vtreat.vtreat_parameters({
+            'filter_to_recommended': False,
+            'user_transforms': [PolyTransform(deg=10)]
+        }))
+
+    # %%
+
+    transform.fit(d, d['y'])
+
+    # %%
+
+    transform.score_frame_
+
+    # %%
+
+    x2_overfit = transform.transform(d)
+
+    # %%
+    # seaborn.scatterplot(x='x', y='y', data=x2_overfit)
+    # seaborn.lineplot(x='x', y='x_poly', data=x2_overfit, color='red', alpha=0.5)
+
+    # %%
+
+    x2 = transform.fit_transform(d, d['y'])
+
+    # %%
+
+    transform.score_frame_
+
+    # %%
+
+    x2.head()
+
+    # %%
+
+    # seaborn.scatterplot(x='x', y='y', data=x2)
+    # seaborn.lineplot(x='x', y='x_poly', data=x2, color='red', alpha=0.5)
+
+    # %%
+
+