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

Before Change

// the rest will have a standard encoding
data_path = fetching.get_data_dir()
fetching.fetch_employee_salaries()
data_file = os.path.join(data_path, "employee_salaries", "rows.csv")
df = pd.read_csv(data_file).astype(str)
df["Current Annual Salary"] = [float(s[1:]) for s
                               in df["Current Annual Salary"]]
df["Year First Hired"] = [int(s.split("/")[-1])
                          for s in df["Date First Hired"]]

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

After Change

// the other column are supposed clean, so it is "safe" to use
// one hot encoding to transform them

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

//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// We then choose  which categorical encoding methods to benchmark:
encoding_methods = ["one-hot", "target", "similarity"]

Instances