pandas简单入门

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.randn(10,5), columns=['col1', 'col2', 'col3', 'col4', 'col5'])
print(df)

df.apply(lambda x: x.sum(), axis=1)
print(df)

def process_age(x):
    age = x[2]
    if age > 0 and age < 30:
        return 0
    elif age >= 30 and age <50:
        return 1
    else:
        return 2

def process(x):
    return x.sum()

#df["ColSum"] = df.apply(process, axis=1)
#df["ColSum"] = df.apply(lambda x: x.sum(), axis=1)
#df["col0/100"] = df.apply(lambda x: x[0]/100, axis=1)
#df["newCol"] = df.apply(lambda x: x[0] * x[2], axis=1)
print(df)

df.col1[df.col1>70] = 0
df.col1[df.col1<=70] = 1