Rename Environment.__init__.cross_validation_params to cv_params,…

… but retain original as an `Alias`

README.md

@@ -64,7 +64,7 @@ env = Environment(
     results_path='path/to/results/directory',  # Where your result files will go
     metrics_map=['roc_auc_score'],  # Callables, or strings referring to `sklearn.metrics`
     cross_validation_type=StratifiedKFold,  # Class, or string in `sklearn.model_selection`
-    cross_validation_params=dict(n_splits=5, shuffle=True, random_state=32)
+    cv_params=dict(n_splits=5, shuffle=True, random_state=32)
 )
 ```
 
@@ -358,7 +358,7 @@ env = Environment(
     results_path='HyperparameterHunterAssets',
     metrics_map=['roc_auc_score'],
     cross_validation_type='StratifiedKFold',
-    cross_validation_params=dict(n_splits=10, shuffle=True, random_state=32),
+    cv_params=dict(n_splits=10, shuffle=True, random_state=32),
 )
 
 # Now, conduct an `Experiment`

docs/quick_start.rst

@@ -22,7 +22,7 @@ Set Up an Environment
 	    results_path="path/to/results/directory",
 	    metrics_map=["roc_auc_score"],
 	    cross_validation_type=StratifiedKFold,
-	    cross_validation_params=dict(n_splits=5, shuffle=2, random_state=32)
+	    cv_params=dict(n_splits=5, shuffle=2, random_state=32)
     )
 
 Individual Experimentation

examples/advanced_examples/do_full_save_example.py

@@ -18,7 +18,7 @@ def execute():
         results_path="HyperparameterHunterAssets",
         metrics_map=["roc_auc_score"],
         cross_validation_type=RepeatedStratifiedKFold,
-        cross_validation_params=dict(n_splits=3, n_repeats=2, random_state=32),
+        cv_params=dict(n_splits=3, n_repeats=2, random_state=32),
         do_full_save=do_full_save,
     )
 

examples/advanced_examples/environment_params.json

@@ -6,7 +6,7 @@
     "f1_score"
   ],
   "cross_validation_type": "StratifiedKFold",
-  "cross_validation_params": {
+  "cv_params": {
     "n_splits": 10,
     "shuffle": true,
     "random_state": 117

examples/advanced_examples/environment_params_path_example.py

@@ -17,7 +17,7 @@ def _execute():
     env = Environment(
         train_dataset=get_breast_cancer_data(),  # If your dataset is a str path, you can even add it to environment_params
         environment_params_path="./environment_params.json",  # Use this file for parameters not explicitly given
-        cross_validation_params=dict(
+        cv_params=dict(
             n_splits=5, shuffle=True, random_state=32
         ),  # Here we decide to override our default values
     )
@@ -30,7 +30,7 @@ def _execute():
     print(env.file_blacklist)  # This includes some other values too, but you can ignore them
     # All of the above are from `environment_params_path`
     print(
-        env.cross_validation_params
+        env.cv_params
     )  # This is the value we provided above, rather than our `environment_params_path` default
 
     experiment = CVExperiment(model_initializer=KNeighborsClassifier, model_init_params={})

examples/advanced_examples/holdout_test_datasets_example.py

@@ -27,7 +27,7 @@ def execute():
         # See the documentation in :class:`environment.Environment` and :class:`metrics.ScoringMixIn` for more information
         metrics_map=["roc_auc_score"],
         cross_validation_type=StratifiedKFold,
-        cross_validation_params=dict(n_splits=5, shuffle=True, random_state=32),
+        cv_params=dict(n_splits=5, shuffle=True, random_state=32),
     )
 
     experiment = CVExperiment(

examples/advanced_examples/lambda_callback_example.py

@@ -33,7 +33,7 @@ def execute():
         results_path="HyperparameterHunterAssets",
         metrics_map=["roc_auc_score"],
         cross_validation_type=RepeatedStratifiedKFold,
-        cross_validation_params=dict(n_splits=5, n_repeats=2, random_state=32),
+        cv_params=dict(n_splits=5, n_repeats=2, random_state=32),
         runs=2,
         # Just instantiate `Environment` with your list of callbacks, and go about business as usual
         experiment_callbacks=[printer_callback(), confusion_matrix_oof()],

examples/advanced_examples/multi_metric_example.ipynb

@@ -70,7 +70,7 @@
     "        f1_macro=lambda y_true, y_pred: f1_score(y_true, y_pred, average=\"macro\"),\n",
     "    ),\n",
     "    cross_validation_type=\"KFold\",\n",
-    "    cross_validation_params=dict(n_splits=10, shuffle=True, random_state=42),\n",
+    "    cv_params=dict(n_splits=10, shuffle=True, random_state=42),\n",
     "    verbose=1,\n",
     ")"
    ]

examples/advanced_examples/multi_metric_example.py

@@ -39,7 +39,7 @@
         f1_macro=lambda y_true, y_pred: f1_score(y_true, y_pred, average="macro"),
     ),
     cross_validation_type="KFold",
-    cross_validation_params=dict(n_splits=10, shuffle=True, random_state=42),
+    cv_params=dict(n_splits=10, shuffle=True, random_state=42),
     verbose=1,
 )
 

examples/advanced_examples/recorder_example.py

@@ -21,7 +21,7 @@
     target_column="diagnosis",
     metrics_map=["roc_auc_score"],
     cross_validation_type=StratifiedKFold,
-    cross_validation_params=dict(n_splits=10, shuffle=True, random_state=32),
+    cv_params=dict(n_splits=10, shuffle=True, random_state=32),
 )
 
 

examples/catboost_examples/classification.ipynb

@@ -261,7 +261,7 @@
     "    target_column=\"y\",\n",
     "    metrics_map=dict(f1=lambda y_true, y_pred: f1_score(y_true, y_pred, average=\"micro\")),\n",
     "    cross_validation_type=KFold,\n",
-    "    cross_validation_params=dict(n_splits=5, random_state=32),\n",
+    "    cv_params=dict(n_splits=5, random_state=32),\n",
     ")"
    ]
   },

examples/catboost_examples/classification.py

@@ -22,7 +22,7 @@
     target_column="y",
     metrics_map=dict(f1=lambda y_true, y_pred: f1_score(y_true, y_pred, average="micro")),
     cross_validation_type=KFold,
-    cross_validation_params=dict(n_splits=5, random_state=32),
+    cv_params=dict(n_splits=5, random_state=32),
 )
 
 # Now that HyperparameterHunter has an active `Environment`, we can do two things:

examples/catboost_examples/regression.ipynb

@@ -260,7 +260,7 @@
     "    results_path=\"HyperparameterHunterAssets\",\n",
     "    metrics_map=dict(evs=explained_variance_score),\n",
     "    cross_validation_type=\"KFold\",\n",
-    "    cross_validation_params=dict(n_splits=3, shuffle=True, random_state=1337),\n",
+    "    cv_params=dict(n_splits=3, shuffle=True, random_state=1337),\n",
     "    runs=2,\n",
     ")"
    ]

examples/catboost_examples/regression.py

@@ -16,7 +16,7 @@
     results_path="HyperparameterHunterAssets",
     metrics_map=dict(evs=explained_variance_score),
     cross_validation_type="KFold",
-    cross_validation_params=dict(n_splits=3, shuffle=True, random_state=1337),
+    cv_params=dict(n_splits=3, shuffle=True, random_state=1337),
     runs=2,
 )
 

examples/extended_example.ipynb

@@ -81,7 +81,7 @@
     "    metrics_map=['roc_auc_score'],\n",
     "    target_column='diagnosis',\n",
     "    cross_validation_type=StratifiedKFold,\n",
-    "    cross_validation_params=dict(n_splits=3, shuffle=True, random_state=32),\n",
+    "    cv_params=dict(n_splits=3, shuffle=True, random_state=32),\n",
     "    file_blacklist=['script_backup']\n",
     ")"
    ]
@@ -96,7 +96,7 @@
     "* A `metrics_map`, with 'roc_auc_score', because the Wisconsin Breast Cancer dataset is a classification problem,\n",
     "* `target_column`, a string naming the column in our dataset containing the target output (defaults to 'target'),\n",
     "* Our `cross_validation_type` imported earlier,\n",
-    "* `cross_validation_params`, a dict containing all the arguments to pass to `cross_validation_type`,\n",
+    "* `cv_params`, a dict containing all the arguments to pass to `cross_validation_type`,\n",
     "* And `file_blacklist`, a list of result file names we don't want to save. Here, we're giving it 'script_backup' because we're executing our Experiments in a Jupyter notebook, instead of a standard Python script\n",
     "\n",
     "Notice that upon instantiation, our `Environment` logs the cross-experiment key produced by the provided parameters. This is important because it determines when two `Experiment`s can be properly compared; we'll go over this more later."

examples/functionality_example.py

@@ -19,7 +19,7 @@ def execute():
         results_path="HyperparameterHunterAssets",
         metrics_map=["roc_auc_score"],
         cross_validation_type="StratifiedKFold",
-        cross_validation_params=dict(n_splits=10, shuffle=True, random_state=32),
+        cv_params=dict(n_splits=10, shuffle=True, random_state=32),
     )
 
     # Now, conduct an `Experiment`

examples/keras_examples/experiment_example.py

@@ -28,7 +28,7 @@ def execute():
         target_column="diagnosis",
         metrics_map=["roc_auc_score"],
         cross_validation_type="StratifiedKFold",
-        cross_validation_params=dict(n_splits=5, shuffle=True, random_state=32),
+        cv_params=dict(n_splits=5, shuffle=True, random_state=32),
     )
 
     experiment = CVExperiment(

examples/keras_examples/image_classification_example.py

@@ -36,7 +36,7 @@ def _execute():
         results_path="HyperparameterHunterAssets",
         metrics_map=["roc_auc_score"],
         cross_validation_type="StratifiedKFold",
-        cross_validation_params=dict(n_splits=3, shuffle=True, random_state=True),
+        cv_params=dict(n_splits=3, shuffle=True, random_state=True),
     )
 
     experiment = CVExperiment(

examples/keras_examples/multi_classification_example.py

@@ -39,7 +39,7 @@ def _execute():
         metrics_map=["roc_auc_score"],
         target_column=[f"target_{_}" for _ in range(10)],
         cross_validation_type="StratifiedKFold",
-        cross_validation_params=dict(n_splits=10, shuffle=True, random_state=True),
+        cv_params=dict(n_splits=10, shuffle=True, random_state=True),
     )
 
     experiment = CVExperiment(

examples/keras_examples/optimization_example.py

@@ -46,7 +46,7 @@ def _execute():
         results_path="HyperparameterHunterAssets",
         metrics_map=["roc_auc_score"],
         cross_validation_type="StratifiedKFold",
-        cross_validation_params=dict(n_splits=5, shuffle=True, random_state=32),
+        cv_params=dict(n_splits=5, shuffle=True, random_state=32),
     )
 
     #################### Experimentation ####################

examples/lightgbm_examples/classification.ipynb

@@ -260,7 +260,7 @@
     "    target_column=\"y\",\n",
     "    metrics_map=dict(f1=lambda y_true, y_pred: f1_score(y_true, y_pred, average=\"micro\")),\n",
     "    cross_validation_type=\"StratifiedKFold\",\n",
-    "    cross_validation_params=dict(n_splits=5, random_state=32),\n",
+    "    cv_params=dict(n_splits=5, random_state=32),\n",
     ")"
    ]
   },

examples/lightgbm_examples/classification.py

@@ -19,7 +19,7 @@
     target_column="y",
     metrics_map=dict(f1=lambda y_true, y_pred: f1_score(y_true, y_pred, average="micro")),
     cross_validation_type="StratifiedKFold",
-    cross_validation_params=dict(n_splits=5, random_state=32),
+    cv_params=dict(n_splits=5, random_state=32),
 )
 
 # Now that HyperparameterHunter has an active `Environment`, we can do two things:

examples/lightgbm_examples/regression.ipynb

@@ -210,7 +210,7 @@
     "    target_column=\"median_value\",\n",
     "    metrics_map=dict(r2=r2_score),\n",
     "    cross_validation_type=RepeatedKFold,\n",
-    "    cross_validation_params=dict(n_repeats=2, n_splits=5, random_state=42),\n",
+    "    cv_params=dict(n_repeats=2, n_splits=5, random_state=42),\n",
     ")"
    ]
   },

examples/lightgbm_examples/regression.py

@@ -18,7 +18,7 @@
     target_column="median_value",
     metrics_map=dict(r2=r2_score),
     cross_validation_type=RepeatedKFold,
-    cross_validation_params=dict(n_repeats=2, n_splits=5, random_state=42),
+    cv_params=dict(n_repeats=2, n_splits=5, random_state=42),
 )
 
 # Now that HyperparameterHunter has an active `Environment`, we can do two things:

examples/rgf_examples/classification.ipynb

@@ -261,7 +261,7 @@
     "    target_column=\"y\",\n",
     "    metrics_map=[\"hamming_loss\"],\n",
     "    cross_validation_type=RepeatedStratifiedKFold,\n",
-    "    cross_validation_params=dict(n_repeats=2, n_splits=10, random_state=1337),\n",
+    "    cv_params=dict(n_repeats=2, n_splits=10, random_state=1337),\n",
     ")"
    ]
   },

examples/rgf_examples/classification.py

@@ -17,7 +17,7 @@
     target_column="y",
     metrics_map=["hamming_loss"],
     cross_validation_type=RepeatedStratifiedKFold,
-    cross_validation_params=dict(n_repeats=2, n_splits=10, random_state=1337),
+    cv_params=dict(n_repeats=2, n_splits=10, random_state=1337),
 )
 
 # Now that HyperparameterHunter has an active `Environment`, we can do two things:

examples/rgf_examples/regression.ipynb

@@ -191,7 +191,7 @@
     "    target_column=\"progression\",\n",
     "    metrics_map=dict(msle=(mean_squared_log_error, \"min\")),\n",
     "    cross_validation_type=\"KFold\",\n",
-    "    cross_validation_params=dict(n_splits=10, random_state=42),\n",
+    "    cv_params=dict(n_splits=10, random_state=42),\n",
     "    runs=3,\n",
     ")"
    ]

examples/rgf_examples/regression.py

@@ -17,7 +17,7 @@
     target_column="progression",
     metrics_map=dict(msle=(mean_squared_log_error, "min")),
     cross_validation_type="KFold",
-    cross_validation_params=dict(n_splits=10, random_state=42),
+    cv_params=dict(n_splits=10, random_state=42),
     runs=3,
 )
 

examples/simple_experiment_example.py

@@ -9,7 +9,7 @@ def execute():
         results_path="HyperparameterHunterAssets",
         metrics_map=["roc_auc_score"],
         cross_validation_type="StratifiedKFold",
-        cross_validation_params=dict(n_splits=5, shuffle=True, random_state=32),
+        cv_params=dict(n_splits=5, shuffle=True, random_state=32),
     )
 
     experiment = CVExperiment(

examples/simple_optimization_example.py

@@ -11,7 +11,7 @@ def _execute():
         target_column="diagnosis",
         metrics_map=["roc_auc_score"],
         cross_validation_type=StratifiedKFold,
-        cross_validation_params=dict(n_splits=10, shuffle=True, random_state=32),
+        cv_params=dict(n_splits=10, shuffle=True, random_state=32),
         runs=2,
     )
 

examples/sklearn_examples/classification.ipynb

@@ -274,7 +274,7 @@
     "    target_column=\"diagnosis\",\n",
     "    metrics_map=[\"roc_auc_score\"],\n",
     "    cross_validation_type=\"StratifiedKFold\",\n",
-    "    cross_validation_params=dict(n_splits=5, random_state=32),\n",
+    "    cv_params=dict(n_splits=5, random_state=32),\n",
     "    verbose=1,\n",
     ")"
    ]

examples/sklearn_examples/classification.py

@@ -22,7 +22,7 @@
     target_column="diagnosis",
     metrics_map=["roc_auc_score"],
     cross_validation_type="StratifiedKFold",
-    cross_validation_params=dict(n_splits=5, random_state=32),
+    cv_params=dict(n_splits=5, random_state=32),
     verbose=1,
 )
 

examples/xgboost_examples/classification.ipynb

@@ -275,7 +275,7 @@
     "    target_column=\"diagnosis\",\n",
     "    metrics_map=[\"roc_auc_score\"],\n",
     "    cross_validation_type=StratifiedKFold,\n",
-    "    cross_validation_params=dict(n_splits=10, shuffle=True, random_state=32),\n",
+    "    cv_params=dict(n_splits=10, shuffle=True, random_state=32),\n",
     ")"
    ]
   },

examples/xgboost_examples/classification.py

@@ -17,7 +17,7 @@
     target_column="diagnosis",
     metrics_map=["roc_auc_score"],
     cross_validation_type=StratifiedKFold,
-    cross_validation_params=dict(n_splits=10, shuffle=True, random_state=32),
+    cv_params=dict(n_splits=10, shuffle=True, random_state=32),
 )
 
 # Now that HyperparameterHunter has an active `Environment`, we can do two things:

examples/xgboost_examples/regression.ipynb

@@ -190,7 +190,7 @@
     "    target_column=\"progression\",\n",
     "    metrics_map=[\"mean_absolute_error\"],\n",
     "    cross_validation_type=\"KFold\",\n",
-    "    cross_validation_params=dict(n_splits=12, shuffle=True, random_state=32),\n",
+    "    cv_params=dict(n_splits=12, shuffle=True, random_state=32),\n",
     "    runs=2,\n",
     ")"
    ]

examples/xgboost_examples/regression.py

@@ -16,7 +16,7 @@
     target_column="progression",
     metrics_map=["mean_absolute_error"],
     cross_validation_type="KFold",
-    cross_validation_params=dict(n_splits=12, shuffle=True, random_state=32),
+    cv_params=dict(n_splits=12, shuffle=True, random_state=32),
     runs=2,
 )
 

hyperparameter_hunter/callbacks/loggers.py

@@ -37,7 +37,7 @@ def on_experiment_start(self):
         super().on_experiment_start()
 
     def on_repetition_start(self):
-        if G.Env.verbose >= 3 and G.Env.cross_validation_params.get("n_repeats", 1) > 1:
+        if G.Env.verbose >= 3 and G.Env.cv_params.get("n_repeats", 1) > 1:
             G.log("", previous_frame=inspect.currentframe().f_back)
         super().on_repetition_start()
 
@@ -77,7 +77,7 @@ def on_fold_end(self):
         content += self.log_separator if not content.endswith(" ") else ""
         content += self.__elapsed_helper("folds")
 
-        if G.Env.verbose >= 2 and G.Env.cross_validation_params["n_splits"] > 1:
+        if G.Env.verbose >= 2 and G.Env.cv_params["n_splits"] > 1:
             G.log(content, previous_frame=inspect.currentframe().f_back, add_time=False)
         else:
             G.debug(content, previous_frame=inspect.currentframe().f_back, add_time=False)
@@ -90,7 +90,7 @@ def on_repetition_end(self):
         content += self.log_separator if not content.endswith(" ") else ""
         content += self.__elapsed_helper("reps")
 
-        if G.Env.verbose >= 2 and G.Env.cross_validation_params.get("n_repeats", 1) > 1:
+        if G.Env.verbose >= 2 and G.Env.cv_params.get("n_repeats", 1) > 1:
             G.log(content, previous_frame=inspect.currentframe().f_back)
         else:
             G.debug(content, previous_frame=inspect.currentframe().f_back)