python 中写hive 脚本

1、直接执行.sql脚本

import numpy as np
import pandas as pd
import lightgbm as lgb
from pandas import DataFrame
from sklearn.model_selection import train_test_split
from io import StringIO
import gc
import sys
import os
hive_cmd = "hive -f ./sql/sql.sql"
output = os.popen(hive_cmd)
data_cart_prop = pd.read_csv(StringIO(unicode(output.read(),'utf-8')), sep="\t",header=0)

　　

2、Hive语句执行

假如有如下hive sql：
hive_cmd = 'hive -e "select count(*) from hbase.routermac_sort_10;"'
一般在python中按照如下方式执行该hive sql：
os.system(hive_cmd)

---------------------

hive_cmd1 = "hive -f ./user.sql"
output1 = os.popen(hive_cmd1)
test_user = pd.read_csv(StringIO(unicode(output1.read(),'utf-8')), sep="\t",header=0)

hive_cmd2 = "hive -f ./action.sql"
output2 = os.popen(hive_cmd2)
test_action = pd.read_csv(StringIO(unicode(output2.read(),'utf-8')), sep="\t",header=0)

hive_cmd3 = "hive -f ./click.sql"
output3 = os.popen(hive_cmd3)
test_click = pd.read_csv(StringIO(unicode(output3.read(),'utf-8')), sep="\t",header=0)

为了显示表头，在脚本中加上一句：set hive.cli.print.header=true;

3、tf 显存占用

import tensorflow as tf
tf.enable_eager_execution()
x = tf.get_variable('x', shape=[1], initializer=tf.constant_initializer(3.))
with tf.GradientTape() as tape:       
    y = tf.square(x)
    y_grad = tape.gradient(y, x)        
print([y.numpy(), y_grad.numpy()])