remove duplicate rows pandas code example
Example 1: drop duplicates pandas first column
import pandas as pd
data = pd.read_csv("employees.csv")
data.sort_values("First Name", inplace = True)
data.drop_duplicates(subset ="First Name",keep = False, inplace = True)
print(data)
Example 2: remove duplicate row in df
df = df.drop_duplicates()
Example 3: remove duplicate columns python dataframe
df = df.loc[:,~df.columns.duplicated()]
Example 4: df remove duplicate rows
df = df.drop_duplicates()
p
Example 5: 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()