关于python 读取csv最快的Datatable的用法,你都学会了吗

import datatable as dt
import pandas as pd
import time
from datetime import date
from datatable import f,update

t0 = time.time()
t1 = time.time() 
file = r"C:\Users\songroom\Desktop\000001.csv"
my_table = dt.fread(file,sep=",",header=True)  ## datatable格式
## dt.fread(data, sep=",",header=False, columns=["A","B","C","D"]) 多种设置
t3 = time.time()
print(f"my_table    ->     data type    ：{type(my_table)}")
print(f"my_table    ->     data name    : {my_table.names}")
print(f"my_table    ->    (nrows,ncols) : {my_table.shape}") # (nrows, ncols) 

print(f"my_table    ->    head(10)      : " )
print(my_table.head(10)) # 
print(f" datatable  read_csv cost  time : {t3-t0} s!")

t4 = time.time() 
pandas_df = pd.read_csv(file) 
t5 = time.time() 
print(f" pandas read_csv cost    time     : {t5-t4} s! ")

t6 = time.time() 
my_table.to_jay(r"C:\Users\songroom\Desktop\000001.jay")
t7 = time.time() 
print(f"datatable 把数据存放成jay cost time : {t7-t6} s!")
## 把.jay文件读成datatable
t8 = time.process_time_ns() ## 增加精度
table_jay = dt.fread(r"C:\Users\songroom\Desktop\000001.jay")
t9 = time.process_time_ns()
print(f"把.jay文件 读取到datatable cost time : {(t9-t8)/1000000000.0} s !")
print(f".jay文件读取成table_jay 的数据格式    ：{type(table_jay)}")

## 把datatable转成pandas.dataframe
t10 = time.time() 
pandas_df = my_table.to_pandas()
t11 = time.time() 
print(f"pandas_df  type : {type(pandas_df)}  ")
print(f"datatable 转成  pandas df cost time : {t11-t10} s!")
print(f"{pandas_df.head()}")

t12 = time.process_time()
my_table_from_df = dt.Frame(pandas_df)
t13 = time.process_time()
print(f"dataframe => datatable  cost time : {t13-t12} s!")
print(f"my_table_from_df type: {type(my_table_from_df)}   pandas_df type : {type(pandas_df)}")

t14 = time.time() 
big_table = dt.repeat(my_table, 10) ## 
t14_1 = time.time()
big_table.to_csv(r"C:\Users\songroom\Desktop\000001_big.csv") 
t15 = time.time() 
print(f"big_table  shape (nrows,ncols  ) : {big_table.shape}")
print(f"datatable 扩展10倍        cost time :  {t14_1-t14}s!")
print(f"datatable 落地csv文件   cost time : {t15-t14_1} s!")

arr_from_table = my_table.to_arrow()
print(f"{type(arr_from_table)}")

dict_data = {"dates" : [date(2000, 1, 5), date(2010, 11, 23), date(2020, 2, 29), None],
          "integers" : range(1, 5),
          "floats" : [10.0, 11.5, 12.3, -13],
          "strings" : ['A', 'B', None, 'D']
          }
table_from_dict = dt.Frame(dict_data)
print(f" dict_data type :{type(dict_data)}   table_from_dict type : {type(table_from_dict)} ")

dict_from_datatable = my_table.to_dict()
print(f" dict_from_datatable  type :{type(dict_from_datatable)}   my_table type : {type(my_table)} ")

my_table_new  = my_table[:, "close"]

table_3800_and    = my_table[(f.close > 3800) & (f.pre_close < 3800),:] 

table_3800_or    = my_table[(f.close > 3800) | (f.pre_close < 3800),:] 

my_table[:, 'date']  ## 选择date列
my_table['date']     ## 同上
my_table[:,["date","close"]] ## 选择 date,close两列
my_table[:,f.close]  ## 选择close
my_table[[1, 2, 3], :] ## 选择相应的行
my_table[range(1, 3), :] ## 选择相应的行

my_list = my_table_new.to_list()

dt1 = dt.rbind(my_table, table_3800_or) ## 这两个table合并,行上进行合并；列上扩展用rbind()
del dt1[:, ['date', 'close']] ## 删除两列
my_table['low_high'] = my_table[:, (f.low + f.high)/2.0] ## 增加一列，赋值方法
my_table[:, update(mean = (f.low+ f.high +f.close)/3.0)] ## 增加一列，update方法
my_table.names = {"low_high": "lowhigh", "mean": "mean_3"} ## 对两列的字段进行重命名

nrows,ncols = my_table.shape
tt0 = time.time()
for i in range(nrows):
    values = my_table[i,:]
tt1 = time.time()
print(f"my_table 循环 cost time :{tt1-tt0} s")