import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import statsmodels.api as sm
import numpy as np

da = pd.read_csv("nhanes_2015_2016.csv")

da["DMDMARTL"] = da.DMDMARTL.fillna("Missing")
da["DMDMARTLdescript"] = da.DMDMARTL.replace({1: "Married", 2: "Widowed", 3: "Divorced", 4: "Separated", 5: "Never married",
                             6: "Living with partner",       77: "Refused", 99: "Don't know"})

da["RIAGENDRx"] = da.RIAGENDR.replace({1: "Male", 2: "Female"})

da["agegrp"] = pd.cut(da.RIDAGEYR, [10, 20, 30, 40, 50, 60, 70, 80])

y = "prop"
dx = da.loc[~da.RIAGENDRx.isin(["Male"]), :]
plt.figure(figsize=(12, 5))
prop_df = (dx["agegrp"]
       .groupby(dx["DMDMARTLdescript"])
       .value_counts(normalize=True)
       .rename(y)
       .reset_index())
sns.barplot(x="agegrp", y=y, hue="DMDMARTLdescript", data=prop_df)