data_cleaning_202001

read_explore_data.py

# import packages
import pandas as pd
import numpy as np
import seaborn as sns

import matplotlib.pyplot as plt
import matplotlib.mlab as mlab
import matplotlib
plt.style.use('ggplot')
from matplotlib.pyplot import figure

%matplotlib inline
matplotlib.rcParams['figure.figsize'] = (12,8)

pd.options.mode.chained_assignment = None



# read the data
df = pd.read_csv('sberbank.csv')

# shape and data types of the data
print(df.shape)
print(df.dtypes)

# select numeric columns
df_numeric = df.select_dtypes(include=[np.number])
numeric_cols = df_numeric.columns.values
print(numeric_cols)

# select non numeric columns
df_non_numeric = df.select_dtypes(exclude=[np.number])
non_numeric_cols = df_non_numeric.columns.values
print(non_numeric_cols)