# Ceteris Lab downloadable Python script
# Course: Fundamentals of Python for Financial Econometrics

import pandas as pd
from io import StringIO

raw = StringIO("date,value\n2026-01-01,2.1\n2026-02-01,NA\n2026-02-01,2.4")
df = pd.read_csv(raw, parse_dates=["date"], na_values=["NA"])
df["is_duplicate_date"] = df.duplicated("date", keep=False)
print(df.isna().sum().to_dict())
print(df["is_duplicate_date"].sum())

def validate_series(frame):
    assert frame["date"].notna().all(), "dates must be present"
    assert frame["date"].is_monotonic_increasing, "dates must be sorted"
    assert frame["value"].dropna().between(-100, 100).all(), "value outside range"
    return True

print(validate_series(df.sort_values("date")))

import pandas as pd
from io import StringIO
raw = StringIO("date,value\n2026-01-01,2.1\n2026-02-01,NA\n2026-02-01,2.4")
df = pd.read_csv(raw, parse_dates=["date"], na_values=["NA"])
df["is_duplicate_date"] = df.duplicated("date", keep=False)
print(df.isna().sum().to_dict())