get unique rows pandas code example
Example 1: pandas unique values in column
df.name.unique()
Example 2: distinct rows in this DataFrame
df.distinct().count()
Example 3: unique entries in column pandas
import pandas as pd
pd.set_option('display.max_row', 1000)
pd.set_option('display.max_columns', 50)
data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
'year': [2012, 2012, 2013, 2014, 2014],
'reports': [4, 24, 31, 2, 3]}
df = pd.DataFrame(data, index = ['Cochice', 'Pima', 'Santa Cruz', 'Maricopa', 'Yuma'])
df
df.name.unique()
Example 4: Return a new DataFrame with duplicate rows removed
from pyspark.sql import Row
df = sc.parallelize([
Row(name='Alice', age=5, height=80),
Row(name='Alice', age=5, height=80),
Row(name='Alice', age=10, height=80)]).toDF()
df.dropDuplicates().show()
df.dropDuplicates(['name', 'height']).show()