upidea

#!/bin/bash

export PATH=/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin

if [[ $ENGINE_CORE_CLICKHOUSE_USER != '' ]]; then
    CLARG="--host ${ENGINE_CORE_CLICKHOUSE_HOST} --port ${ENGINE_CORE_CLICKHOUSE_PORT} --user ${ENGINE_CORE_CLICKHOUSE_USER} --password ${ENGINE_CORE_CLICKHOUSE_PASSWORD}"
elif [[ $ENGINE_CORE_CLICKHOUSE_HOST != '' ]]; then
    CLARG="--host ${ENGINE_CORE_CLICKHOUSE_HOST} --port ${ENGINE_CORE_CLICKHOUSE_PORT}"
else
    CLARG="--host 127.0.0.1 --port 9000"

upidea

# tf-idf （term frequency - inverse document frequency） 
# 常用于挖掘文章的关键词；  
#       在同一篇文章内值大的表示该词在这篇文章中有较高区分度：
#           在该篇文章中反复出现， 而在全部文档中出现较少(逆文档频率)
#       整个语料中值大的， 并无特别的意义， 不适于跨文章比较

# 词频向量化
from sklearn.feature_extraction.text import CountVectorizer
 
# token_pattern 参数设置来指定字符切分字符串：  r"(?u)\b[^@]+\b     '\\b\\w+\\b'

upidea

# Format data
out = "\n".join([
            " ".join([
                f"{data[i+1]:02x}{data[i]:02x}"
                for i in range(line, min(line + 256, length), 16)
            ])
            for line in range(0, length, 256)
        ])

upidea

import mmap
import struct

print(struct.unpack('<i', b'\xa0\xcf\x6e\x44'))   # 1148112800
struct.unpack('>i', b'\x95\x6b\x31\x93')    # -1788137069


with open('tmp', 'rb', 0) as file, \
     mmap.mmap(file.fileno(), 0, access=mmap.ACCESS_READ) as s:
     pos = s.find(b'\x64\x65')

upidea

def dense_to_one_hot(labels_dense, num_classes):
  """Convert class labels from scalars to one-hot vectors."""
  num_labels = labels_dense.shape[0]
  index_offset = numpy.arange(num_labels) * num_classes
  labels_one_hot = numpy.zeros((num_labels, num_classes))
  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
  return labels_one_hot


看起来 这是一段代码 

upidea

# 直接用numpy做数据打散、划分
data = pad_sequences(sequences, maxlen=MAX_SEQUENCE_LENGTH)


labels = to_categorical(np.asarray(labels))
print('Shape of Data Tensor:', data.shape)
print('Shape of Label Tensor:', labels.shape)

indices = np.arange(data.shape[0])
np.random.shuffle(indices)

upidea

class Metrics(tf.keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.confusion = []
        self.precision = []
        self.recall = []
        self.f1s = []
        self.kappa = []
        self.auc = []

    def on_epoch_end(self, epoch, logs={}):

upidea

import os
import re
import requests
import json
import time
import datetime
import genanki

my_model = genanki.Model(
    201901021920,

upidea

select to_char('2018-04-26 22:23:40', 'yyyyMMdd');
select date_format('2018-04-26 22:23:40', 'yyyyMMdd');
select date_format('2018-04-26 22:23:40', 'yyyy-MM-dd HH:mm:ss');
select to_char('2018-04-26 22:23:40', 'yyyy-MM-dd hh24:mi:ss'); 
select date_format(to_unix_timestamp(nvl('2018-04-26 22:23:40', '')), 'yyyyMMdd');
select from_unixtime(unix_timestamp('20171205  22:23:40','yyyymmdd  HH:mm:ss'),'yyyy-mm-dd HH-mm-ss');

upidea

package topic

import spark.broadcast._
import spark.SparkContext
import spark.SparkContext._
import spark.RDD
import spark.storage.StorageLevel
import scala.util.Random
import scala.math.{ sqrt, log, pow, abs, exp, min, max }
import scala.collection.mutable.HashMap