pandas

#python3 pandas, make sure csv is in the right place
import numpy as np
import pandas as pd
from matplotlib.pyplot import hist

#######################################################

matrix = np.random.randint(0,100,size=(100, 4))
print(matrix)
print(matrix[90:100,0])

random_df = pd.DataFrame(matrix, columns=list('ABCD'))
random_df['A']
random_df['A'].plot.hist()
############################################################

# generate 100 observations from random normal distribution 
# with mean of 5 and SD of 2
new_col = np.random.normal(loc=5, scale=2, size=100)
# add it as a new column to our dataframe
random_df['E'] = new_col
random_df['E'].plot.hist()
#############################################################

labels = np.random.choice(['A_1', 'A_2', 'B_1', 'B_2'], size=100)
random_df['labels'] = labels
list(random_df)
################################################################33

label_group = random_df['labels'].str.split('_')
print(label_group)
random_df['group'] = label_group.str[0]
random_df.head()
########################################################

random_df.describe(include='all')
random_df.groupby('group')['A', 'B'].mean()
df_summary = random_df.groupby('group').mean()
###########################################################

mtcars = pd.read_csv('/home/cdo/mtcars.csv')
list(mtcars)
mtcars.describe()
# rename column with make and model
mtcars.rename(columns={"Unnamed: 0": 'model'}, inplace=True)
list(mtcars)

##Test!