原创 python 排序
import numpy as np print(np.argmax(xx), np.argmin(xx)) # 最大值索引值 mm = np.arange(10) np.random.shuffle(mm) # 隨機打亂m
原创 python 日期爲昨天
# method 1: import arrow yesterday = arrow.utcnow().to('local').shift(days=-1).format('YYYY-MM-DD') print(yesterda
原创 81022905327754
81022905327754
原创 以太坊
以太幣在中國生根落地,引得市場紛紛側目,然而在價格已經創下歷史新高的時刻,以太幣的到來,國外的學者已經指出在整個以太幣的智能合約交易中,10%是龐氏騙局,也就是說有人在藉以太坊平臺發融資項目獲得資金,而以太幣則成爲一種媒介,這些融
原创 一口氣安裝完keras,tensorflow,pytorch,opencv
這篇作廢 我的下一篇纔是安裝tensorflow及keras真理 環境: anaconda4.2;python3.5;windows10,64,cuda 先前辛苦的cuda9.1無用,大家想用gpu一定要選cuda8.0,我以爲官
原创 python3--map,reduce,filter,zip
# coding=utf-8 pool1 = [1,2,3,4] pool2 = ['a','b','c','d'] ## map() r1 = list(map(lambda x: x*2,pool1)) print(r1)
原创 用pyspark的方式寫count(case when)
import pyspark.sql.functions as fn ff = lambda cond: fn.countDistinct(fn.when(cond,df['s_id']).otherwise(None)) co
原创 sql自然周統計
-- 最近2個自然周統計: SELECT count(CASE WHEN (int(datediff(scheduled_date,'2001-01-01')/7) IN (int(datediff(CURRENT_DA
原创 pysaprk求max
#column:A,B # Method 1: Use describe() float(df.describe("A").filter("summary = 'max'").select("A").collect()[0].a
原创 pyspark中"and"條件使用注意
def getLevel(ltv): return fn.when((lv >= 6.81) & (lv <= 10.00),'S')\ .otherwise( fn.when((lv >= 6.08)
原创 kafka-python_&&_pysparkStreamingContext
# coding=utf-8 from pyspark import SparkContext from pyspark.streaming import StreamingContext sc = SparkContext("
原创 pyspark&pandas之字符串篩選dataframe
#pandas: import numpy as np import pandas as pd df = pd.DataFrame(np.array([['banana',1],['apple',2],['pear',3]]).re
原创 matplotlib_linux作圖_時間序列
## linux: import matplotlib matplotlib.use('Agg') import matplotlib.pyplot as plt import matplotlib.dates as mdates
原创 pyspark之分組排序
import pyspark.sql.functions as fn from pyspark.sql import Window df.withColumn("row_number", fn.row_number().over(W
原创 pyspark_dataframe
from __future__ import division,print_function import time import datetime import numpy as np import pandas as pd fro