pandas数据分析100道练习题-第二部分

import pandas as pd
ser = pd.Series(['01 Jan 2010', 
                '02-02-2011', 
                 '20120303', 
                 '2013/04/04', 
                 '2014-05-05', 
                 '2015-06-06T12:20'])

pd.to_datetime(ser)

date = pd.Series(['01 Jan 2010', 
                '02-02-2011', 
                 '20120303', 
                 '2013/04/04', 
                 '2014-05-05', 
                 '2015-06-06T12:20'])
date = pd.to_datetime(date)
date.dt.year

date.dt.month

date.dt.day

date.dt.hour

ser = pd.Series(['Apple', 'Orange', 'Plan', 'Python', 'Money'])

def count(x):
    aims = 'aeiou'
    c= 0
    for i in x:
        if i in aims:
            c += 1
    return c

counts = ser.map(lambda x: count(x))
ser[counts>=2]

emails = pd.Series(['buying books at amazom.com', 
                    'rameses@egypt.com', 
                    'matt@t.co',
                    'narendra@modi.com'])

import re
pattern ='[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Za-z]{2,4}'
valid = emails.str.findall(pattern, flags=re.IGNORECASE)
[x[0] for x in valid if len(x)]

import numpy as np
fruit = pd.Series(np.random.choice(['apple', 'banana', 'carrot'], 10))
weights = pd.Series(np.linspace(1, 10, 10))

weights.groupby(fruit).mean()

p = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
q = pd.Series([10, 9, 8, 7, 6, 5, 4, 3, 2, 1])

sum((p - q)**2)**.5

ser = pd.Series([2, 10, 3, 4, 9, 10, 2, 7, 3])
dd = np.diff(np.sign(np.diff(ser)))
peak_locs = np.where(dd == -2)[0] + 1
peak_locs

pd.Series(np.random.randint(1,10,10), 
          pd.date_range('2000-01-02', 
                        periods=10, 
                        freq='W-SAT'))

ser = pd.Series([1,10,3,np.nan], index=pd.to_datetime(['2000-01-01',
                                                       '2000-01-03', 
                                                       '2000-01-06', 
                                                       '2000-01-08']))
# 使用前一个日期的数据填补
ser.resample('D').ffill()
# 如果使用后一个日期的数据填补, 可以使用bfill方法

ser = pd.Series(np.arange(20) + np.random.normal(1, 10, 20))
autocorrelations = [ser.autocorr(i).round(2) for i in range(11)]

autocorrelations

# 生成用于测试的csv
fpath = 'testt.csv'
df = pd.DataFrame({'a': range(100), 
                   'b':np.random.choice(['apple', 'banana', 'carrot'], 100)})
df.to_csv(fpath, index=None)

### 隔行读取csv
import csv

with open(fpath, 'r') as f:
    reader = csv.reader(f)
    out = []
    for i, row in enumerate(reader):
        if i%20 ==0:
            out.append(row)
pd.DataFrame(out[1:], columns=out[0])

pd.read_csv(fpath, 
            converters={
                'a':lambda x: 'low' if int(x) < 50 else 'high'
            }).head()

pd.read_csv(fpath, usecols=['a']).head()

df=pd.DataFrame(
    {
        'a':range(100),
        'b':np.random.rand(100),
        'c':[1,2,3,4]*25,
        'd':['apple', 'banana', 'carrot']*33 + ['apple']
    }
)

df.dtypes

df.shape

df.describe()

df.loc[df.a==np.max(df.a)]

np.where(df.c==np.max(df.c))

row = 4
col = 0
print(f'行{row}列{col}的值是: {df.iat[row, col]}')
row = 4
col = 2
print(f'行{row}列{col}的值是: {df.iat[row, col]}')
row = 0
col = 0
print(f'行{row}列{col}的值是: {df.iat[row, col]}')
row = 33
col = 3
print(f'行{row}列{col}的值是: {df.iat[row, col]}')

index = 0
col = 'd'
print(f'index={index}, col={col} : {df.at[index, col]}')
index = 2
col = 'd'
print(f'index={index}, col={col} : {df.at[index, col]}')
index = 4
col = 'd'
print(f'index={index}, col={col} : {df.at[index, col]}')
index = 5
col = 'c'
print(f'index={index}, col={col} : {df.at[index, col]}')

df.rename(columns={'d':'fruit'}).head()