pandas数据分析100道练习题-第三部分

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'a':[1.2,2,3,4],
    'b':list('abcd')
})

print('缺失:', df.isnull().values.any())
df.iat[0,0] = np.nan
print('缺失:', df.isnull().values.any())

df.apply(lambda x: x.isnull().sum())

df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')
df[['Min.Price', 'Max.Price']].head()

# 仅使用['Min.Price', 'Max.Price']这两列演示
df[['Min.Price', 'Max.Price']].apply(lambda x: x.fillna(x.mean())).head()

# 只要传入一个list作为切片
df[['Manufacturer']].head()

df = pd.DataFrame(np.arange(20).reshape(-1, 5), columns=list('abcde'))
df.head()

df[list('cbdae')]

# 设置之前
df

pd.set_option('display.max_columns', 4)
pd.set_option('display.max_rows', 4)
# 设置之后
df

pd.set_option('display.max_columns', 10)
pd.set_option('display.max_rows', 10)

pd.DataFrame(np.random.random(4)**10, columns=['random'])

pd.set_option('display.float_format', lambda x: '%.4f' % x)
pd.DataFrame(np.random.random(4)**10, columns=['random'])

# 恢复默认值
pd.set_option('display.float_format', None)
pd.DataFrame(np.random.random(4)**10, columns=['random'])

df = pd.DataFrame(np.random.random(4), columns=['random'])
df

df.style.format({'random':'{0:.2%}'.format})

df = pd.read_csv(
    'https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv', 
    usecols=[0,1,2,3,5])

df[['Manufacturer', 'Model', 'Type']] = df[['Manufacturer', 'Model', 'Type']].fillna('missing')
df.index = df.Manufacturer + '_' + df.Model + '_' + df.Type
print(df.index.is_unique)

df = pd.DataFrame(
    np.random.randint(1, 30, 30).reshape(10,-1), 
    columns=list('abc'))
df['a']

# 使用行号排序
df['a'].argsort()

# 可以这样看到原始数据的排序

df['a'][df['a'].argsort()]

n = 5
df['a'].argsort()[::-1][n]

df = pd.DataFrame(np.random.randint(10, 40, 60).reshape(-1, 4))
rowsums = df.apply(np.sum, axis=1)
last_two_rows = df.iloc[np.where(rowsums > 100)[0][-2:], :]
last_two_rows

# Input
ser = pd.Series(np.logspace(-2, 2, 30))

# Solution
def cap_outliers(ser, low_perc, high_perc):
    low, high = ser.quantile([low_perc, high_perc])
    print(low_perc, '%ile: ', low, '|', high_perc, '%ile: ', high)
    ser[ser < low] = low
    ser[ser > high] = high
    return(ser)

capped_ser = cap_outliers(ser, .05, .95)

df = pd.DataFrame(np.random.randint(-20, 50, 100).reshape(10,-1))
print(df)

# 步骤1:删除负数

arr = df[df > 0].values.flatten()
arr_qualified = arr[~np.isnan(arr)]
arr_qualified

# 步骤2: 计算正方形的边长

n = int(np.floor(arr_qualified.shape[0]**.5))
n

# 步骤3: 整形为要求的正方形
top_indexes = np.argsort(arr_qualified)[::-1]
output = np.take(arr_qualified, sorted(top_indexes[:n**2])).reshape(n, -1)
print(output)

df = pd.DataFrame(np.arange(25).reshape(5, -1))
df

a, b = df.iloc[1, :].copy(), df.iloc[2, :].copy()
df.iloc[1, :], df.iloc[2, :] = b, a
df

df.iloc[::-1, :]

df = pd.DataFrame(np.arange(25).reshape(5,-1), columns=list('abcde'))
df

pd.concat([pd.get_dummies(df['a']), df[list('bcde')]], axis=1)

df = pd.DataFrame(np.random.randint(1,100, 40).reshape(10, -1))
df.apply(np.argmax, axis=1)

nearest = {}
for i, row in df.iterrows():
    c = ((df - row)**2).sum(axis = 1).argsort()
    for j in c:
        if j != i:
            break
    nearest[i] = j
print(nearest)