import pandas as pd

redW = pd.read_csv('winequality-red.csv',sep=';')
whiteW = pd.read_csv('winequality-white.csv',sep=';')

redW.head()
redW.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1599 entries, 0 to 1598
Data columns (total 12 columns):
fixed acidity           1599 non-null float64
volatile acidity        1599 non-null float64
citric acid             1599 non-null float64
residual sugar          1599 non-null float64
chlorides               1599 non-null float64
free sulfur dioxide     1599 non-null float64
total sulfur dioxide    1599 non-null float64
density                 1599 non-null float64
pH                      1599 non-null float64
sulphates               1599 non-null float64
alcohol                 1599 non-null float64
quality                 1599 non-null int64
dtypes: float64(11), int64(1)
memory usage: 150.0 KB

redW.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1359 entries, 0 to 1598
Data columns (total 12 columns):
fixed acidity           1359 non-null float64
volatile acidity        1359 non-null float64
citric acid             1359 non-null float64
residual sugar          1359 non-null float64
chlorides               1359 non-null float64
free sulfur dioxide     1359 non-null float64
total sulfur dioxide    1359 non-null float64
density                 1359 non-null float64
pH                      1359 non-null float64
sulphates               1359 non-null float64
alcohol                 1359 non-null float64
quality                 1359 non-null int64
dtypes: float64(11), int64(1)
memory usage: 138.0 KB

sum(redW.duplicated())

0

redW.drop_duplicates(inplace=True)

redW['density'].mean()

0.9967089477557027