confusion balancer - and more! (#197)

* that was easier than expected * base tests are now green * added a flake fix * tests are green! * added abalone dataset * added datasets for abalone * added the heroes dataset, for the horde and whatnot * added proper documentation now too * fixed dataframe thign * 00ps in the docs fixed
koaning · Sep 22, 2019 · 963874e · 963874e
1 parent 41e249c
commit 963874e
Show file tree

Hide file tree

Showing 9 changed files with 4,679 additions and 32 deletions.
diff --git a/doc/meta.ipynb b/doc/meta.ipynb
diff --git a/doc/pandas_pipeline.ipynb b/doc/pandas_pipeline.ipynb
@@ -40,7 +40,7 @@
    "source": [
     "from sklego.datasets import load_chicken\n",
     "from sklego.pandas_utils import log_step\n",
-    "chickweight = load_chicken(True)"
+    "chickweight = load_chicken(give_pandas=True)"
    ]
   },
   {
@@ -84,7 +84,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "INFO:__main__:[set_dtypes(df)] n_obs=578 n_col=4 time=0:00:00.003478\n"
+      "INFO:__main__:[set_dtypes(df)] n_obs=578 n_col=4 time=0:00:00.003235\n"
      ]
     },
     {
@@ -181,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -198,7 +198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "metadata": {
     "scrolled": true
    },
@@ -207,9 +207,9 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "INFO:__main__:[set_dtypes(df)] n_obs=578 n_col=4 time=0:00:00.001948\n",
-      "DEBUG:__main__:[remove_dead_chickens(df)] n_obs=519 n_col=4 time=0:00:00.003613\n",
-      "INFO:__main__:[remove_outliers(df)] n_obs=519 n_col=4 time=0:00:00.004420\n"
+      "INFO:__main__:[set_dtypes(df)] n_obs=578 n_col=4 time=0:00:00.002340\n",
+      "DEBUG:__main__:[remove_dead_chickens(df)] n_obs=519 n_col=4 time=0:00:00.005238\n",
+      "INFO:__main__:[remove_outliers(df)] n_obs=519 n_col=4 time=0:00:00.006010\n"
      ]
     },
     {
@@ -288,7 +288,7 @@
        "4      76     8     1    1"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -306,15 +306,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "INFO:__main__:[set_dtypes(df)] n_obs=578 n_col=4 time=0:00:00.001979\n",
-      "INFO:__main__:[remove_outliers(df)] n_obs=519 n_col=4 time=0:00:00.003608\n"
+      "INFO:__main__:[set_dtypes(df)] n_obs=578 n_col=4 time=0:00:00.002603\n",
+      "INFO:__main__:[remove_outliers(df)] n_obs=519 n_col=4 time=0:00:00.003335\n"
      ]
     },
     {
@@ -393,7 +393,7 @@
        "4      76     8     1    1"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -424,5 +424,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }