pandera_dataframe_schema_validation_with_column_type_constraints.py

1import pandas as pd
2import pandera as pa
3
4# data to validate
5df = pd.DataFrame({
6    "column1": [1, 4, 0, 10, 9],
7    "column2": [-1.3, -1.4, -2.9, -10.1, -20.4],
8    "column3": ["value_1", "value_2", "value_3", "value_2", "value_1"],
9})
10
11# define schema
12schema = pa.DataFrameSchema({
13    "column1": pa.Column(int, pa.Check.le(10)),
14    "column2": pa.Column(float, pa.Check.lt(-1.2)),
15    "column3": pa.Column(str, pa.Check.str_startswith("value_")),
16})
17
18validated_df = schema(df)
19print(validated_df)