Python Data Analysis Part 3: Education of Respondents

education.py

import pandas as pd
from os import getcwd, path
import plotly.express as px
import plotly.offline as pyo
pyo.init_notebook_mode()

path_to_data = path.join(getcwd(), "data", "survey_results_public.csv")
data = pd.read_csv(path_to_data)

data = data[["EdLevel"]]

data = data.dropna()
print(f"Rows left: {data.shape[0]:,}")

data.loc[:, "EdLevel"] = data.loc[:, "EdLevel"].map(
    lambda response: 
        "Master's degree" if (response == "Master’s degree (M.A., M.S., M.Eng., MBA, etc.)")
        else "Bachelor's degree" if (response == "Bachelor’s degree (B.A., B.S., B.Eng., etc.)")
        else "High School" if (response == "Secondary school (e.g. American high school, German Realschule or Gymnasium, etc.)")
        else "Professional degree" if (response == "Professional degree (JD, MD, etc.)")
        else "Associate degree" if (response == "Associate degree (A.A., A.S., etc.)")
        else "Higher Ed. study w/o degree" if (response == "Some college/university study without earning a degree")
        else "Doctoral degree" if (response == "Other doctoral degree (Ph.D., Ed.D., etc.)")
        else "Elementary school" if (response == "Primary/elementary school")
        else "No formal education" if (response == "I never completed any formal education")
        else response
)

ed_level_counts = data["EdLevel"].value_counts(ascending=True)

fig = px.bar(
    ed_level_counts, 
    title="Education Level of Respondents",
    orientation="h"
)
fig.update_layout(
    xaxis_title = "Frequency",
    yaxis_title = "Education Level",
    title_x = 0.5,
    showlegend = False
)
fig.show()