import pandas as pd
import matplotlib.pyplot as plt

mypl = pd.read_csv("Data/clean_pl.csv", low_memory=False)

# get wages
# mypl_2019 = mypl[mypl.syear == 2019]
mask = pd.to_numeric(mypl["plc0013_h"], errors="coerce").isna()
mypl = mypl[~mask]
mypl["plc0013_h"] = pd.to_numeric(mypl["plc0013_h"].values)
mypl = mypl[mypl["plc0013_h"] < 12000]
ids = mypl.pid

# plot histogram of wages
plt.style.use(["science"])
fig, ax = plt.subplots(figsize=(7, 5))
ax.hist(mypl["plc0013_h"], bins=20, rwidth=0.9)
ax.tick_params('x', rotation=60)
ax.set_xticks([2000, 4000, 6000, 8000, 10000, 12000])
ax.set_xlabel("Bruttoverdienst letzten Monat [EUR]")
fig.tight_layout()
plt.show()


biojob = pd.read_stata("Data/biojob.dta")
bioedu = pd.read_stata("Data/bioedu.dta")

biojob = biojob[biojob.pid.isin(ids)]
bioedu = bioedu[bioedu.pid.isin(ids)]


biojob.fulltime.value_counts()
biojob.einstieg_artk.value_counts()
biojob.isco88.value_counts()

bioedu.gebjahr.value_counts()

exp_data = pd.DataFrame()
exp_data["pid"] = ids
exp_data[""]