python
import pandas as pd
import numpy as np
import scipy.stats as stats
python
data = pd.read_csv('data.csv')
python
data.dropna()
data.drop_duplicates()
data['column_name'] = data['column_name'].astype(int)
python
mean_value = data['column_name'].mean()
frequency = data['column_name'].value_counts()
t_statistic, p_value = stats.ttest_ind(data['column_name1'], data['column_name2'])
python
data['column_name'].plot.hist()
data['column_name'].plot.line()
data.plot.scatter(x='column_name1', y='column_name2')
