add LawSchoolAdmissionBar dataset

Author: jfparie

datasets/__init__.py

@@ -0,0 +1,14 @@
+import pandas as pd
+from pathlib import Path
+import json
+
+
+data_folder = Path(__file__).resolve().parent / "data"
+dtypes_path = (data_folder / "dtypes.json")
+csv_path = str(data_folder / "adult.data")
+
+
+with dtypes_path.open('r') as f:
+    dtypes = json.load(f)
+columns = list(dtypes.keys())
+df = pd.read_csv(csv_path, header=None, names=columns).astype(dtypes)

datasets/adult/__init__.py

@@ -0,0 +1,14 @@
+import pandas as pd
+from pathlib import Path
+import json
+
+
+data_folder = Path(__file__).resolve().parent / "data"
+dtypes_path = (data_folder / "dtypes.json")
+csv_path = str(data_folder / "bar_pass_prediction.csv")
+
+
+with dtypes_path.open('r') as f:
+    dtypes = json.load(f)
+columns = list(dtypes.keys())
+df = pd.read_csv(csv_path, skiprows=1, sep=';', header=None, names=columns).astype(dtypes)

datasets/data/bar_pass_prediction.csv

@@ -0,0 +1,14 @@
+import pandas as pd
+from pathlib import Path
+import json
+
+
+data_folder = Path(__file__).resolve().parent / "data"
+dtypes_path = (data_folder / "dtypes.json")
+csv_path = str(data_folder / "winequality-white.csv")
+
+
+with dtypes_path.open('r') as f:
+    dtypes = json.load(f)
+columns = list(dtypes.keys())
+df = pd.read_csv(csv_path, skiprows=1, sep=';', header=None, names=columns).astype(dtypes)

datasets/law school admission bar/__init__.py

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -305,7 +305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -314,7 +314,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -339,7 +339,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -487,7 +487,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -612,7 +612,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -938,7 +938,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -983,7 +983,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {