在下面的脚本中,我发现GridSearchCV启动的作业似乎挂起了.
import json
import pandas as pd
import numpy as np
import unicodedata
import re
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.decomposition import TruncatedSVD
from sklearn.linear_model import SGDClassifier
import sklearn.cross_validation as CV
from sklearn.grid_search import GridSearchCV
from nltk.stem import WordNetLemmatizer
# Seed for randomization. Set to some definite integer for debugging and set to None for production
seed = None
### Text processing functions ###
def normalize(string):#Remove diacritics and whatevs
return "".join(ch.lower() for …