pyspark&pandas之字符串筛选dataframe

#pandas:
import numpy as np
import pandas as pd

df = pd.DataFrame(np.array([['banana',1],['apple',2],['pear',3]]).reshape(3,2))
df.columns = ['a','b']
df2 = df[df['a'].str.contains('l')]
print(df2)

       a  b
1  apple  2

#pyspark:
ddf = spark.createDataFrame(df)
ddf2 = ddf[ddf['a'].like('%l%')]
ddf2.show()