#363 Remove duplicate rows from pandas database

data.csv

            first column second column
0   GGAGCAGCGAGGCAACCGGG    TTCTGGCAGT
1   CGAGCGTATGATAGCAACTT    TGGAGGTTGC
2   CGTATGGTCGCCTTTCTCCA    ACAGGGGGCT
3   AAAGTTCGTGTACCTCTATG    ACATACCTGT
4   AAAGTTCGTGTACCTCTATG    ACATACCTGT
5   AAAGTTCGTGTACCTCTATG    ACATACCTGT
6   AAAGTTCGTGTACCTCTATG    ACATACCTGT
7   AAAGTTCGTGTACCTCTATG    ACATACCTGT
8   AAAGTTCGTGTACCTCTATG    ACATACCTGT
9   AAAGTTCGTGTACCTCTATG    ACATACCTGT
10  AAAGTTCGTGTACCTCTATG    ACATACCTGT
11  AAAGTTCGTGTACCTCTATG    ACATACCTGT
12  GGAGCAGCGAGGCAACCGGG    TTCTGGCAGT

import pandas as pd
df = pd.read_csv('data.csv')
print(df)
df = df.drop_duplicates()
print(df)

Output:

           first column second column
0  GGAGCAGCGAGGCAACCGGG    TTCTGGCAGT
1  CGAGCGTATGATAGCAACTT    TGGAGGTTGC
2  CGTATGGTCGCCTTTCTCCA    ACAGGGGGCT
3  AAAGTTCGTGTACCTCTATG    ACATACCTGT

Last Updated on 2023-07-17 by gantovnik