import time 
from tqdm import tqdm 
'''
更多Python学习资料以及源码教程资料，可以在群821460695 免费获取
'''
data_file = open('sample-data.txt', 'r') 
distance_between_city = data_file.readline().split() 
queries = data_file.readlines() 
print('SIZE OF ARRAY = ', len(distance_between_city)) 
print('TOTAL NUMBER OF QUERIES = ', len(queries)) 
data_file.close() 
# 分配要执行的查询数 
execute_queries = 2000 
print('\n\nExecuting',execute_queries,'Queries') 
# FOR循环方法 
# 读取文件并存储距离和查询 
start_time_for_loop = time.time() 
data_file = open('sample-data.txt', 'r') 
distance_between_city = data_file.readline().split() 
queries = data_file.readlines() 
# 存储距离的列表 
distances_for_loop = [] 
# 计算开始索引和结束索引之间的距离的函数 
def calculateDistance(startIndex, endIndex): 
 distance = 0 
 for number in range(startIndex, endIndex+1, 1): 
 distance += int(distance_between_city[number]) 
 return distance 
for query in tqdm(queries[:execute_queries]): 
 query = query.split() 
 startIndex = int(query[0]) 
 endIndex = int(query[1]) 
 distances_for_loop.append(calculateDistance(startIndex,endIndex)) 
data_file.close() 
# 获取结束时间 
end_time_for_loop = time.time() 
print('\n\nTime Taken to execute task by for loop :', (end_time_for_loop-start_time_for_loop),'seconds') 
# 前缀数组方法 
# 读取文件并存储距离和查询 
start_time_for_prefix = time.time() 
data_file = open('sample-data.txt', 'r') 
distance_between_city = data_file.readline().split() 
queries = data_file.readlines() 
# 存储距离列表 
distances_for_prefix_array = [] 
# 创建前缀数组 
prefix_array = [] 
prefix_array.append(int(distance_between_city[0])) 
for i in range(1, 100000, 1): 
 prefix_array.append((int(distance_between_city[i]) + prefix_array[i-1])) 
for query in tqdm(queries[:execute_queries]): 
 query = query.split() 
 startIndex = int(query[0]) 
 endIndex = int(query[1]) 
 if startIndex == 0: 
 distances_for_prefix_array.append(prefix_array[endIndex]) 
 else: 
 distances_for_prefix_array.append((prefix_array[endIndex]-prefix_array[startIndex-1])) 
data_file.close() 
end_time_for_prefix = time.time() 
print('\n\nTime Taken by Prefix Array to execute task is : ', (end_time_for_prefix-start_time_for_prefix), 'seconds') 
# 检查结果 
correct = True 
for result in range(0,execute_queries): 
 if distances_for_loop[result] != distances_for_prefix_array[result] : 
 correct = False 
if correct: 
 print('\n\nDistance calculated by both the methods matched.') 
else: 
 print('\n\nResults did not matched!!') 

''' 
优化方法：apply方法 
''' 
# 导入库 
import pandas as pd  
import numpy as np 
import time 
import math 
data = pd.read_csv('train_E6oV3lV.csv') 
# 打印头部信息 
print(data.head()) 
# 使用dataframe iterows计算字符数 
print('\n\nUsing Iterrows\n\n') 
start_time = time.time() 
data_1 = data.copy() 
n_words = [] 
for i, row in data_1.iterrows(): 
 n_words.append(len(row['tweet'].split())) 
data_1['n_words'] = n_words  
print(data_1[['id','n_words']].head()) 
end_time = time.time() 
print('\nTime taken to calculate No. of Words by iterrows :', 
(end_time-start_time),'seconds') 
# 使用Numpy数组计算字符数 
print('\n\nUsing Numpy Arrays\n\n') 
start_time = time.time() 
data_2 = data.copy() 
n_words_2 = [] 
for row in data_2.values: 
 n_words_2.append(len(row[2].split())) 
data_2['n_words'] = n_words_2 
print(data_2[['id','n_words']].head()) 
end_time = time.time() 
print('\nTime taken to calculate No. of Words by numpy array : ', 
(end_time-start_time),'seconds') 
# 使用apply方法计算字符数 
print('\n\nUsing Apply Method\n\n') 
start_time = time.time() 
data_3 = data.copy() 
data_3['n_words'] = data_3['tweet'].apply(lambda x : len(x.split())) 
print(data_3[['id','n_words']].head()) 
end_time = time.time() 
print('\nTime taken to calculate No. of Words by Apply Method : ', 
(end_time-start_time),'seconds') 

# 导入库 
import pandas as pd 
data = pd.read_csv('school.csv') 
data.head() 

# 将热门城市保存在列表中 
top_cities = ['Brooklyn','Bronx','Manhattan','Jamaica','Long Island City'] 
# 使用loc更新目标 
data.loc[(data.City.isin(top_cities) == False),'City'] = 'Others' 
# 各个城市的频数 
data.City.value_counts() 

''' 
优化方法：向量化函数 
''' 
# 导入库 
import pandas as pd  
import numpy as np 
import time 
import math 
data = pd.read_csv('train_E6oV3lV.csv') 
# 输出头部信息 
print(data.head()) 
def word_count(x) : 
 return len(x.split()) 
# 使用Dataframe iterrows 计算词的个数 
print('\n\nUsing Iterrows\n\n') 
start_time = time.time() 
data_1 = data.copy() 
n_words = [] 
for i, row in data_1.iterrows(): 
 n_words.append(word_count(row['tweet'])) 
data_1['n_words'] = n_words  
print(data_1[['id','n_words']].head()) 
end_time = time.time() 
print('\nTime taken to calculate No. of Words by iterrows :', 
(end_time-start_time),'seconds') 
# 使用向量化方法计算词的个数 
print('\n\nUsing Function Vectorization\n\n') 
start_time = time.time() 
data_2 = data.copy() 
# 向量化函数 
vec_word_count = np.vectorize(word_count) 
n_words_2 = vec_word_count(data_2['tweet']) 
data_2['n_words'] = n_words_2 
print(data_2[['id','n_words']].head()) 
end_time = time.time() 
print('\nTime taken to calculate No. of Words by numpy array : ', 
(end_time-start_time),'seconds') 

# 导入库 
import pandas as pd 
import math 
import multiprocessing as mp 
from random import randint 
# 计算除数的函数 
def countDivisors(n) :  
 count = 0 
 for i in range(1, (int)(math.sqrt(n)) + 1) :  
 if (n % i == 0) :  
%%time 
pool = mp.Pool(processes = (mp.cpu_count() - 1)) 
answer = pool.map(countDivisors,random_data) 
pool.close() 
pool.join() 
​
 if (n / i == i) :  
​
 count = count + 1 
​
 else :  
​
 count = count + 2 
​
 return count  
​
# 创建随机数  
​
random_data = [randint(10,1000) for i in range(1,1000001)] 
​
data = pd.DataFrame({'Number' : random_data }) 
​
data.shape 

%%time 
data['Number_of_divisor'] = data.Number.apply(countDivisors) 

%%time 
pool = mp.Pool(processes = (mp.cpu_count() - 1)) 
answer = pool.map(countDivisors,random_data) 
pool.close() 
pool.join()