# Descriptive Statistics in Python
# Module 0 - Descriptive statistics in Python
# Dataset: /data/wage_sample.csv

# Descriptive Statistics in Python
#
# Use pandas to summarize wage, education, and experience before estimating any model.

# %% Cell 2
import pandas as pd

df = pd.read_csv("wage_sample.csv")
print(df[["wage", "education", "experience"]].describe())

# %% Cell 3
print("Average wage:", round(df["wage"].mean(), 2))
print("Median wage:", round(df["wage"].median(), 2))
print("Wage standard deviation:", round(df["wage"].std(), 2))

# %% Cell 4
grouped = df.groupby("education")["wage"].mean()
print(grouped)

# Interpretation prompt
#
# Write one sentence describing the typical wage and one sentence describing wage spread.