Document & lint code

notebooks/test2.ipynb

@@ -48,7 +48,7 @@
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "Fraud: 0.244% 196\nValid: 99.755% 80234\nX.shape (1196, 28)  y.shape (1196,)\nFraud: 16.722% 200\nValid: 83.278% 996\n"
+     "text": "Fraud: 0.244% 196\nValid: 99.755% 80234\nX.shape (1196, 28)  y.shape (1196,)\nFraud: 16.472% 197\nValid: 83.528% 999\n"
     }
    ],
    "source": [
@@ -103,7 +103,7 @@
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9797\nClassifier's accuracy (test) : 0.9749\nroot\nroot - Down\nroot - Down - Down, <cgaf> - Leaf class=1.0 belief=0.984127 counts=(array([0., 1.]), array([  2, 124]))\nroot - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([5]))\nroot - Up\nroot - Up - Down, <cgaf> - Leaf class=0.0 belief=0.750000 counts=(array([0., 1.]), array([3, 1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0.0 belief=0.980029 counts=(array([0., 1.]), array([687,  14]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9809\nClassifier's accuracy (test) : 0.9749\nroot\nroot - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([124]))\nroot - Up, <cgaf> - Leaf class=0.0 belief=0.977560 counts=(array([0., 1.]), array([697,  16]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9869\nClassifier's accuracy (test) : 0.9749\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([129]))\nroot - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([2]))\nroot - Up, <cgaf> - Leaf class=0.0 belief=0.984419 counts=(array([0., 1.]), array([695,  11]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9869\nClassifier's accuracy (test) : 0.9777\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([129]))\nroot - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([2]))\nroot - Up, <cgaf> - Leaf class=0.0 belief=0.984419 counts=(array([0., 1.]), array([695,  11]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9916\nClassifier's accuracy (test) : 0.9833\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([131]))\nroot - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([8]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([5]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0.0 belief=0.989855 counts=(array([0., 1.]), array([683,   7]))\n\n**************************************************\n0.2235 secs\n"
+     "text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9737\nClassifier's accuracy (test) : 0.9805\nroot\nroot - Down, <cgaf> - Leaf class=1 belief= 0.945736 counts=(array([0, 1]), array([  7, 122]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up, <cgaf> - Leaf class=0 belief= 0.978784 counts=(array([0, 1]), array([692,  15]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9809\nClassifier's accuracy (test) : 0.9805\nroot\nroot - Down, <cgaf> - Leaf class=1 belief= 0.983871 counts=(array([0, 1]), array([  2, 122]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.980170 counts=(array([0, 1]), array([692,  14]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9904\nClassifier's accuracy (test) : 0.9777\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([122]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([8]))\nroot - Up - Up, <cgaf> - Leaf class=0 belief= 0.988669 counts=(array([0, 1]), array([698,   8]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9916\nClassifier's accuracy (test) : 0.9721\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([125]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([5]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.990071 counts=(array([0, 1]), array([698,   7]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9940\nClassifier's accuracy (test) : 0.9749\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([128]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.992867 counts=(array([0, 1]), array([696,   5]))\n\n**************************************************\n0.2412 secs\n"
     }
    ],
    "source": [
@@ -123,7 +123,13 @@
    "cell_type": "code",
    "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "[[0.97223657 0.02776343]\n [0.96965421 0.03034579]\n [0.96918057 0.03081943]\n [0.94009975 0.05990025]]\n"
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "from sklearn.preprocessing import StandardScaler\n",
@@ -133,7 +139,7 @@
     "cclf = CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)\n",
     "cclf.fit(Xtrain, ytrain)\n",
     "res = cclf.predict_proba(Xtest)\n",
-    "#an array containing probabilities of belonging to the 1st class"
+    "print(res[:4, :])"
    ]
   },
   {
@@ -144,7 +150,7 @@
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([131]))\nroot - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([8]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([5]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0.0 belief=0.989855 counts=(array([0., 1.]), array([683,   7]))\n"
+     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([128]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.992867 counts=(array([0, 1]), array([696,   5]))\n"
     }
    ],
    "source": [
@@ -161,7 +167,7 @@
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([131]))\nroot - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([8]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0.0 belief=1.000000 counts=(array([0.]), array([5]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1.0 belief=1.000000 counts=(array([1.]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0.0 belief=0.989855 counts=(array([0., 1.]), array([683,   7]))\n"
+     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([128]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.992867 counts=(array([0, 1]), array([696,   5]))\n"
     }
    ],
    "source": [
@@ -189,7 +195,7 @@
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "1 functools.partial(<function check_no_attributes_set_in_init at 0x12aabb320>, 'Stree')\n2 functools.partial(<function check_estimators_dtypes at 0x12aab0440>, 'Stree')\n3 functools.partial(<function check_fit_score_takes_y at 0x12aab0320>, 'Stree')\n4 functools.partial(<function check_sample_weights_pandas_series at 0x12aaaac20>, 'Stree')\n5 functools.partial(<function check_sample_weights_not_an_array at 0x12aaaad40>, 'Stree')\n6 functools.partial(<function check_sample_weights_list at 0x12aaaae60>, 'Stree')\n7 functools.partial(<function check_sample_weights_shape at 0x12aaaaf80>, 'Stree')\n8 functools.partial(<function check_sample_weights_invariance at 0x12aaac0e0>, 'Stree')\n9 functools.partial(<function check_estimators_fit_returns_self at 0x12aab6440>, 'Stree')\n10 functools.partial(<function check_estimators_fit_returns_self at 0x12aab6440>, 'Stree', readonly_memmap=True)\n11 functools.partial(<function check_complex_data at 0x12aaac290>, 'Stree')\n12 functools.partial(<function check_dtype_object at 0x12aaac200>, 'Stree')\n13 functools.partial(<function check_estimators_empty_data_messages at 0x12aab0560>, 'Stree')\n14 functools.partial(<function check_pipeline_consistency at 0x12aab0200>, 'Stree')\n15 functools.partial(<function check_estimators_nan_inf at 0x12aab0680>, 'Stree')\n16 functools.partial(<function check_estimators_overwrite_params at 0x12aabb200>, 'Stree')\n17 functools.partial(<function check_estimator_sparse_data at 0x12aaaab00>, 'Stree')\n18 functools.partial(<function check_estimators_pickle at 0x12aab08c0>, 'Stree')\n19 functools.partial(<function check_classifier_data_not_an_array at 0x12aabb560>, 'Stree')\n20 functools.partial(<function check_classifiers_one_label at 0x12aab0f80>, 'Stree')\n21 functools.partial(<function check_classifiers_classes at 0x12aab69e0>, 'Stree')\n22 functools.partial(<function check_estimators_partial_fit_n_features at 0x12aab09e0>, 'Stree')\n23 functools.partial(<function check_classifiers_train at 0x12aab60e0>, 'Stree')\n24 functools.partial(<function check_classifiers_train at 0x12aab60e0>, 'Stree', readonly_memmap=True)\n25 functools.partial(<function check_classifiers_train at 0x12aab60e0>, 'Stree', readonly_memmap=True, X_dtype='float32')\n26 functools.partial(<function check_classifiers_regression_target at 0x12aabf050>, 'Stree')\n27 functools.partial(<function check_supervised_y_no_nan at 0x12aaa0c20>, 'Stree')\n28 functools.partial(<function check_supervised_y_2d at 0x12aab6680>, 'Stree')\n29 functools.partial(<function check_estimators_unfitted at 0x12aab6560>, 'Stree')\n30 functools.partial(<function check_non_transformer_estimators_n_iter at 0x12aabbb90>, 'Stree')\n31 functools.partial(<function check_decision_proba_consistency at 0x12aabf170>, 'Stree')\n32 functools.partial(<function check_fit2d_predict1d at 0x12aaac7a0>, 'Stree')\n33 functools.partial(<function check_methods_subset_invariance at 0x12aaac950>, 'Stree')\n34 functools.partial(<function check_fit2d_1sample at 0x12aaaca70>, 'Stree')\n35 functools.partial(<function check_fit2d_1feature at 0x12aaacb90>, 'Stree')\n36 functools.partial(<function check_fit1d at 0x12aaaccb0>, 'Stree')\n37 functools.partial(<function check_get_params_invariance at 0x12aabbdd0>, 'Stree')\n38 functools.partial(<function check_set_params at 0x12aabbef0>, 'Stree')\n39 functools.partial(<function check_dict_unchanged at 0x12aaac3b0>, 'Stree')\n40 functools.partial(<function check_dont_overwrite_parameters at 0x12aaac680>, 'Stree')\n41 functools.partial(<function check_fit_idempotent at 0x12aabf320>, 'Stree')\n42 functools.partial(<function check_n_features_in at 0x12aabf3b0>, 'Stree')\n"
+     "text": "1 functools.partial(<function check_no_attributes_set_in_init at 0x12a2f1200>, 'Stree')\n2 functools.partial(<function check_estimators_dtypes at 0x12a2e7320>, 'Stree')\n3 functools.partial(<function check_fit_score_takes_y at 0x12a2e7200>, 'Stree')\n4 functools.partial(<function check_sample_weights_pandas_series at 0x12a2d7b00>, 'Stree')\n5 functools.partial(<function check_sample_weights_not_an_array at 0x12a2d7c20>, 'Stree')\n6 functools.partial(<function check_sample_weights_list at 0x12a2d7d40>, 'Stree')\n7 functools.partial(<function check_sample_weights_shape at 0x12a2d7e60>, 'Stree')\n8 functools.partial(<function check_sample_weights_invariance at 0x12a2d7f80>, 'Stree')\n9 functools.partial(<function check_estimators_fit_returns_self at 0x12a2ec320>, 'Stree')\n10 functools.partial(<function check_estimators_fit_returns_self at 0x12a2ec320>, 'Stree', readonly_memmap=True)\n11 functools.partial(<function check_complex_data at 0x12a2e2170>, 'Stree')\n12 functools.partial(<function check_dtype_object at 0x12a2e20e0>, 'Stree')\n13 functools.partial(<function check_estimators_empty_data_messages at 0x12a2e7440>, 'Stree')\n14 functools.partial(<function check_pipeline_consistency at 0x12a2e70e0>, 'Stree')\n15 functools.partial(<function check_estimators_nan_inf at 0x12a2e7560>, 'Stree')\n16 functools.partial(<function check_estimators_overwrite_params at 0x12a2f10e0>, 'Stree')\n17 functools.partial(<function check_estimator_sparse_data at 0x12a2d79e0>, 'Stree')\n18 functools.partial(<function check_estimators_pickle at 0x12a2e77a0>, 'Stree')\n19 functools.partial(<function check_classifier_data_not_an_array at 0x12a2f1440>, 'Stree')\n20 functools.partial(<function check_classifiers_one_label at 0x12a2e7e60>, 'Stree')\n21 functools.partial(<function check_classifiers_classes at 0x12a2ec8c0>, 'Stree')\n22 functools.partial(<function check_estimators_partial_fit_n_features at 0x12a2e78c0>, 'Stree')\n23 functools.partial(<function check_classifiers_train at 0x12a2e7f80>, 'Stree')\n24 functools.partial(<function check_classifiers_train at 0x12a2e7f80>, 'Stree', readonly_memmap=True)\n25 functools.partial(<function check_classifiers_train at 0x12a2e7f80>, 'Stree', readonly_memmap=True, X_dtype='float32')\n26 functools.partial(<function check_classifiers_regression_target at 0x12a2f1ef0>, 'Stree')\n27 functools.partial(<function check_supervised_y_no_nan at 0x12a2d8b00>, 'Stree')\n28 functools.partial(<function check_supervised_y_2d at 0x12a2ec560>, 'Stree')\n29 functools.partial(<function check_estimators_unfitted at 0x12a2ec440>, 'Stree')\n30 functools.partial(<function check_non_transformer_estimators_n_iter at 0x12a2f1a70>, 'Stree')\n31 functools.partial(<function check_decision_proba_consistency at 0x12a2f6050>, 'Stree')\n32 functools.partial(<function check_fit2d_predict1d at 0x12a2e2680>, 'Stree')\n33 functools.partial(<function check_methods_subset_invariance at 0x12a2e2830>, 'Stree')\n34 functools.partial(<function check_fit2d_1sample at 0x12a2e2950>, 'Stree')\n35 functools.partial(<function check_fit2d_1feature at 0x12a2e2a70>, 'Stree')\n36 functools.partial(<function check_fit1d at 0x12a2e2b90>, 'Stree')\n37 functools.partial(<function check_get_params_invariance at 0x12a2f1cb0>, 'Stree')\n38 functools.partial(<function check_set_params at 0x12a2f1dd0>, 'Stree')\n39 functools.partial(<function check_dict_unchanged at 0x12a2e2290>, 'Stree')\n40 functools.partial(<function check_dont_overwrite_parameters at 0x12a2e2560>, 'Stree')\n41 functools.partial(<function check_fit_idempotent at 0x12a2f6200>, 'Stree')\n42 functools.partial(<function check_n_features_in at 0x12a2f6290>, 'Stree')\n43 functools.partial(<function check_requires_y_none at 0x12a2f6320>, 'Stree')\n"
     }
    ],
    "source": [