catalystfrank

# When processing Sequence Tagging problems,
# An accuracy func which is too strict is not convergence-friendly.
# This Func is the solution of a naive leetcode problem LCS (Largest Common Subsequence),
# Original All-Correct-Or-Nothing accuracy function takes 7x times long to achieve certain accuracy.

def LCS(p,l):
    if len(p)==0:
        return 0
    P = np.array(list(p)).reshape((1,len(p)))
    L = np.array(list(l)).reshape((len(l),1))

catalystfrank

import numpy as np
import pandas as pd
import numpy.random as nr

# Read In
DF = pd.read_csv('train.csv',sep=',',header=0)
for i in xrange(28):
    DF[str(i)] = DF['Target'].map(lambda x: int(str(i) in x.split(' ')))

value_counts =  DF.ix[:,2:].apply(np.sum, axis=0)

catalystfrank

import numpy as np
import pandas as pd
import bottleneck as bn

# Read And Count
trainDF = pd.read_csv('train.csv',sep=',',header=0)
lenTrain = len(trainDF)
valDF = pd.read_csv('submission.csv',sep=',',header=0)
lenVal = len(valDF)
trainFold = pd.read_csv('train_5fold_20181219.csv',sep=',',header=0)

catalystfrank

```mermaid
flowchart
	A("是真的吗") --> |"SERP i.e. Perplexity"| B["是什么"] 
	A --> |"Deep (re)Search i.e. ODR/Grok3"| C("为什么") 
	A -->|"科学观 i.e. 卡尔-波普尔"| D("如何重现或证伪")
	B --> |"专家网络 i.e. 微信/LinkedIn"| B1("行业专家觉得是什么")
	C --> |"Think i.e. R1"| C1("逻辑观点")
	C --> |"Multi Agent i.e. MGX/Camel"| C2("博弈观点")
	D --> |"直觉"| D1("重现解构") 
	D --> |"Deep (re)Search i.e. ODR/Grok3"| D2("反例")