validating columns in pandas on the basis of dtypes
import pandas as pd
import pandera as pa
df = pd.DataFrame({
"column1": [1, 2, 3],
"column2": ["a", "b", "c"],
})
column1_schema = pa.Column(pa.Int, name="column1")
column2_schema = pa.Column(pa.String, name="column2")
# pass the dataframe as an argument to the Column object callable
df = column1_schema(df)
validated_df = column2_schema(df)
# or explicitly use the validate method
df = column1_schema.validate(df)
validated_df = column2_schema.validate(df)
# use the DataFrame.pipe method to validate two columns
validated_df = df.pipe(column1_schema).pipe(column2_schema)