yingminc

yingminc

#encoding: utf-8
from gensim.corpora import WikiCorpus
import codecs
import os

path_for_save_resault = '/home/ubuntu/Documents/hw_background_gene/'

wiki_jpn = WikiCorpus('/home/ubuntu/Documents/hw_background_gene/jawiki-latest-pages-articles.xml.bz2')

with codecs.open(os.path.join(path_for_save_resault,"wiki_jpn.txt") , "w" ,'utf-8') as output:

yingminc

Ensembling guide

Guide:

https://mlwave.com/kaggle-ensembling-guide/

Code:

https://github.com/MLWave/Kaggle-Ensemble-Guide

Voting ensembles:

Average predictions from multiple already trained models (easiest to setup). See error correcting codes (like repetition codes).

yingminc

import pandas as pd
import numpy as np
from sklearn.metrics import confusion_matrix,f1_score
from bokeh.io import show, output_file
from bokeh.models import (ColumnDataSource,HoverTool,FixedTicker,PrintfTickFormatter)
from bokeh.plotting import figure

def prabtoclass(series,hold):
    #turn probability to binary label by target threshold
    return [1 if i>=hold else 0 for i in series]

yingminc

yingminc

yingminc

#-*- encoding: utf-8 -*-
from __future__ import division
import math
import struct
import numpy as np
from multiprocessing import Pool, Value, Array
from sklearn.manifold import TSNE
import scipy
import codecs
import argparse

yingminc

import pandas as pd
from datetime import datetime,timedelta

def dealwithshit(d):
   return d.apply(lambda x: x.split(' ')[0] if isinstance(x,str) else x).replace({'--':0}).apply(pd.to_numeric,errors='coerce')




class ob:

yingminc

# coding: utf-8
import pandas as pd

from bokeh.core.properties import field
from bokeh.io import curdoc,output_notebook
from bokeh.layouts import layout,widgetbox,row
from bokeh.models import (
    ColumnDataSource, HoverTool, SingleIntervalTicker, Slider,DateRangeSlider, Button, Label,RelativeDelta,
    CategoricalColorMapper,HBox, Select

yingminc