discretized data

.gitignore

@@ -1,3 +1,4 @@
+.ipynb_checkpoints
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -20,7 +21,6 @@ parts/
 sdist/
 var/
 wheels/
-pip-wheel-metadata/
 share/python-wheels/
 *.egg-info/
 .installed.cfg
@@ -50,6 +50,7 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+cover/
 
 # Translations
 *.mo
@@ -72,6 +73,7 @@ instance/
 docs/_build/
 
 # PyBuilder
+.pybuilder/
 target/
 
 # Jupyter Notebook
@@ -82,7 +84,9 @@ profile_default/
 ipython_config.py
 
 # pyenv
-.python-version
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
@@ -127,3 +131,11 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+.vscode/

data_preprossing.ipynb

@@ -0,0 +1,49 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df = pd.read_csv(\"responses_clean.csv\", sep=\"|\")\n",
+    "\n",
+    "labels = [\"Very Low\", \"Low\", \"Mid\", \"High\", \"Very High\"]\n",
+    "\n",
+    "df['SalaryUSD'] = pd.qcut(df['SalaryUSD'], q = 5, labels=labels)\n",
+    "\n",
+    "df.to_csv(\"responses_discretized.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python (default)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}