f70e71d5c7fdc8e25391e54e74c3402fb323ad5c,examples/plot_employee_salaries.py,,,#,45

Before Change

columns_to_encode = {
    "one-hot": ["Gender", "Department Name", "Assignment Category"],
    "num": ["Year First Hired"]}

After Change

import pandas as pd
from dirty_cat.datasets import fetch_employee_salaries

description = fetch_employee_salaries()
df = pd.read_csv(description["path"]).astype(str)

////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// and carry out some basic preprocessing:
df["Current Annual Salary"] = df["Current Annual Salary"].str.strip("$").astype(
    float)
df["Date First Hired"] = pd.to_datetime(df["Date First Hired"])
df["Year First Hired"] = df["Date First Hired"].apply(lambda x: x.year)

target_column = "Current Annual Salary"
y = df[target_column].values.ravel()

Instances