halegreen

package com.hq.modules.executor.service.impl;

import com.alibaba.fastjson.JSON;
import com.hq.common.utils.GenericSuperclassUtil;
import com.hq.common.utils.HttpResult;
import com.hq.common.utils.HttpUtils;
import com.shaw.common.model.RoadLink;
import com.shaw.common.model.TaskInfo;
import com.shaw.common.model.TrafficLightModel;
import com.shaw.common.model.TrafficStateData;

halegreen

## for category columns
def category_feature2FFM(data, category_list):
    previous_len = 0
    for i in range(len(category_list)):
        
        category_name = category_list[i]
        
        dic = data[category_name].unique()
        dic = dict(zip(dic, range(len(dic))))

halegreen

from datetime import datetime
from csv import DictReader
from math import exp, log, sqrt,pow
import itertools
import math
from random import random,shuffle,uniform,seed
import pickle
import sys

seed(1024)

halegreen

class Ensemble(object):
    def __init__(self, n_splits, stacker, base_models):
        self.n_splits = n_splits
        self.stacker = stacker
        self.base_models = base_models

    def fit_predict(self, X, y, T):
        X = np.array(X)
        y = np.array(y)
        T = np.array(T)

halegreen

def generate_batch(data, batch_size, skip_window):
    """
    Generates a mini-batch of training data for the training CBOW
    embedding model.
    :param data (numpy.ndarray(dtype=int, shape=(corpus_size,)): holds the
        training corpus, with words encoded as an integer
    :param batch_size (int): size of the batch to generate
    :param skip_window (int): number of words to both left and right that form
        the context window for the target word.
    Batch is a vector of shape (batch_size, 2*skip_window), with each entry for the batch containing all the context words, with the corresponding label being the word in the middle of the context

halegreen

import numpy as np
import pandas as pd
from sklearn.model_selection import KFold
import dill as pickle
import sys

def input_data(train_file):
    with open(train_file, 'rb') as f1:
       train_data = pickle.load(f1)
    cat_feature = []