Merge branch 'release/v0.1.2'

maks-sh · May 2, 2020 · 9e4baa6 · 9e4baa6
2 parents 7854df2 + fd17ee2
commit 9e4baa6
Show file tree

Hide file tree

Showing 10 changed files with 309 additions and 228 deletions.
diff --git a/docs/changelog.md b/docs/changelog.md
@@ -8,6 +8,23 @@
 * 🔨 something that previously didn’t work as documentated – or according to reasonable expectations – should now work.
 * ❗️ you will need to change your code to have the same effect in the future; or a feature will be removed in the future.
 
+## Version 0.1.2
+
+### [sklift.models](https://scikit-uplift.readthedocs.io/en/latest/api/models.html)
+
+* 🔨 Fix bugs in [TwoModels](https://scikit-uplift.readthedocs.io/en/latest/api/models.html#sklift.models.models.TwoModels) for regression problem.
+* 📝 Minor code refactoring.
+
+### [sklift.metrics](https://scikit-uplift.readthedocs.io/en/latest/api/metrics.html)
+
+* 📝 Minor code refactoring.
+
+### [sklift.viz](https://scikit-uplift.readthedocs.io/en/latest/api/viz.html)
+
+* 💥 Add bar plot in [plot_uplift_by_percentile](https://scikit-uplift.readthedocs.io/en/latest/api/viz.html#sklift.viz.base.plot_uplift_by_percentile) by [@ElisovaIra](https://github.com/ElisovaIra).
+* 🔨 Fix bug in [plot_uplift_by_percentile](https://scikit-uplift.readthedocs.io/en/latest/api/viz.html#sklift.viz.base.plot_uplift_by_percentile).
+* 📝 Minor code refactoring.
+
 ## Version 0.1.1
 
 ### [sklift.viz](https://scikit-uplift.readthedocs.io/en/latest/api/viz.html)

diff --git a/docs/conf.py b/docs/conf.py
@@ -33,7 +33,7 @@ def get_version():
 # -- Project information -----------------------------------------------------
 
 project = 'scikit-uplift'
-author = 'Maksim Shevchenko'
+author = 'Maksim Shevchenko and Contributors'
 copyright = "{}, {}".format(datetime.datetime.now().year, author)
 
 # The full version, including alpha/beta/rc tags
@@ -46,8 +46,11 @@ def get_version():
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    "sphinx.ext.autodoc", "sphinx.ext.viewcode", "sphinx.ext.mathjax", "sphinx.ext.napoleon",
-    "recommonmark"
+    "sphinx.ext.autodoc",
+    "sphinx.ext.viewcode",
+    "sphinx.ext.mathjax",
+    "sphinx.ext.napoleon",
+    "recommonmark",
 ]
 
 master_doc = 'index'
@@ -58,7 +61,7 @@ def get_version():
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store', 'Readme.rst']
 
 
 # -- Options for HTML output -------------------------------------------------

diff --git a/notebooks/RetailHero.ipynb b/notebooks/RetailHero.ipynb
@@ -107,8 +107,8 @@
    "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:37.492036Z",
-     "start_time": "2020-04-28T09:24:37.488584Z"
+     "end_time": "2020-05-02T17:07:22.372375Z",
+     "start_time": "2020-05-02T17:07:22.368436Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -126,7 +126,7 @@
     "urllib.request.urlretrieve(url, '/content/retail_hero.zip')\n",
     "\n",
     "!unzip /content/retail_hero.zip\n",
-    "!pip install scikit-uplift==0.1.1 catboost=0.22"
+    "!pip install scikit-uplift==0.1.2 catboost=0.22"
    ]
   },
   {
@@ -144,8 +144,8 @@
    "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:40.783897Z",
-     "start_time": "2020-04-28T09:24:37.503470Z"
+     "end_time": "2020-05-02T17:07:25.384054Z",
+     "start_time": "2020-05-02T17:07:22.383222Z"
     },
     "colab": {},
     "colab_type": "code",
@@ -196,8 +196,8 @@
    "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:42.100096Z",
-     "start_time": "2020-04-28T09:24:40.786498Z"
+     "end_time": "2020-05-02T17:07:26.483716Z",
+     "start_time": "2020-05-02T17:07:25.386480Z"
     },
     "colab": {},
     "colab_type": "code",
@@ -251,8 +251,8 @@
    "execution_count": 4,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:44.483576Z",
-     "start_time": "2020-04-28T09:24:42.102707Z"
+     "end_time": "2020-05-02T17:07:28.491581Z",
+     "start_time": "2020-05-02T17:07:26.486312Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -313,8 +313,8 @@
    "execution_count": 5,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:44.511016Z",
-     "start_time": "2020-04-28T09:24:44.486035Z"
+     "end_time": "2020-05-02T17:07:28.514717Z",
+     "start_time": "2020-05-02T17:07:28.494500Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -484,8 +484,8 @@
    "execution_count": 6,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:45.715602Z",
-     "start_time": "2020-04-28T09:24:44.514353Z"
+     "end_time": "2020-05-02T17:07:29.570605Z",
+     "start_time": "2020-05-02T17:07:28.518362Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -545,8 +545,8 @@
    "execution_count": 7,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:47.941480Z",
-     "start_time": "2020-04-28T09:24:45.719641Z"
+     "end_time": "2020-05-02T17:07:31.489869Z",
+     "start_time": "2020-05-02T17:07:29.572733Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -632,8 +632,8 @@
    "execution_count": 8,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:50.571779Z",
-     "start_time": "2020-04-28T09:24:47.944822Z"
+     "end_time": "2020-05-02T17:07:33.865281Z",
+     "start_time": "2020-05-02T17:07:31.494251Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -694,8 +694,8 @@
    "execution_count": 9,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:52.942803Z",
-     "start_time": "2020-04-28T09:24:50.576741Z"
+     "end_time": "2020-05-02T17:07:36.709646Z",
+     "start_time": "2020-05-02T17:07:33.871512Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -758,8 +758,8 @@
    "execution_count": 10,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:52.964396Z",
-     "start_time": "2020-04-28T09:24:52.945544Z"
+     "end_time": "2020-05-02T17:07:36.726223Z",
+     "start_time": "2020-05-02T17:07:36.712564Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -858,8 +858,8 @@
    "execution_count": 11,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:56.505700Z",
-     "start_time": "2020-04-28T09:24:53.019392Z"
+     "end_time": "2020-05-02T17:07:39.436995Z",
+     "start_time": "2020-05-02T17:07:36.729508Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -874,7 +874,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/Users/Maksim/Library/Python/3.6/lib/python/site-packages/ipykernel_launcher.py:2: UserWarning: It is recommended to use this approach on treatment balanced data. Current sample size is unbalanced.\n",
+      "/Users/Maksim/Library/Python/3.6/lib/python/site-packages/ipykernel_launcher.py:6: UserWarning: It is recommended to use this approach on treatment balanced data. Current sample size is unbalanced.\n",
       "  \n"
      ]
     },
@@ -891,10 +891,15 @@
     }
    ],
    "source": [
-    "cm_full = ClassTransformation(CatBoostClassifier(iterations=20, thread_count=2, random_state=42, silent=True))\n",
-    "cm_full = cm_full.fit(X_train_full, y_train_full, treat_train_full, estimator_fit_params={'cat_features': [1]})\n",
+    "ct_full = ClassTransformation(CatBoostClassifier(iterations=20, thread_count=2, random_state=42, silent=True))\n",
+    "ct_full = ct_full.fit(\n",
+    "    X_train_full, \n",
+    "    y_train_full, \n",
+    "    treat_train_full, \n",
+    "    estimator_fit_params={'cat_features': cat_features}\n",
+    ")\n",
     "\n",
-    "X_test.loc[:, 'uplift'] = cm_full.predict(X_test.values)\n",
+    "X_test.loc[:, 'uplift'] = ct_full.predict(X_test.values)\n",
     "\n",
     "sub = X_test[['uplift']].to_csv('sub1.csv')\n",
     "\n",
@@ -906,8 +911,8 @@
    "execution_count": 12,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-04-28T09:24:56.560018Z",
-     "start_time": "2020-04-28T09:24:56.508541Z"
+     "end_time": "2020-05-02T17:07:39.478855Z",
+     "start_time": "2020-05-02T17:07:39.440546Z"
     },
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -988,12 +993,12 @@
     }
    ],
    "source": [
-    "cm_full_fi = pd.DataFrame({\n",
-    "    'feature_name': cm_full.estimator.feature_names_,\n",
-    "    'feature_score': cm_full.estimator.feature_importances_\n",
+    "ct_full_fi = pd.DataFrame({\n",
+    "    'feature_name': ct_full.estimator.feature_names_,\n",
+    "    'feature_score': ct_full.estimator.feature_importances_\n",
     "}).sort_values('feature_score', ascending=False).reset_index(drop=True)\n",
     "\n",
-    "cm_full_fi"
+    "ct_full_fi"
    ]
   },
   {