tfidf_columns = ["Title", "FullDescription", "LocationRaw"]
dio = DataIO("Settings.json")
vectorizer = TfidfVectorizer(max_features=200,
norm='l1',
smooth_idf=True,
sublinear_tf=False,
use_idf=True)
short_id = "tfidf_200f_l1"
type_n = "train"
type_v = "valid"
dio.make_counts(vectorizer, short_id, tfidf_columns, "train", "valid")
columns = ["Category", "ContractTime", "ContractType"]
le_features = dio.get_le_features(columns, "train_full")
extra_features = dio.get_features(columns, type_n, le_features)
extra_valid_features = dio.get_features(columns, type_v, le_features)
features = dio.join_features("%s_" + type_n + "_" + short_id + "_matrix",
tfidf_columns, extra_features)
validation_features = dio.join_features(
"%s_" + type_v + "_" + short_id + "_matrix", tfidf_columns,
extra_valid_features)
print features.shape
print validation_features.shape
run = raw_input("OK (Y/N)?")
print run
if run != "Y":
os.exit()
files = joblib.dump(features,
from data_io import DataIO
from sklearn.decomposition import RandomizedPCA
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.base import clone
from sklearn.cross_validation import cross_val_score
import numpy as np
dio = DataIO("Settings.json")
title_corpus = dio.read_gensim_corpus("train_title_nltk_filtered.corpus.mtx")
pca = RandomizedPCA(random_state=3465343)
salaries = dio.get_salaries("train", log=True)
columns = ["Category", "ContractTime", "ContractType"]
le_features = dio.get_le_features(columns, "train_full")
extra_features = dio.get_features(columns, "train", le_features)
#extra_valid_features = dio.get_features(columns, "valid", le_features)
param = "RandomizedPCA title 200 Fulldescription 200 " + ",".join(columns)
print map(len, extra_features)
extra_features = map(lambda x: np.reshape(np.array(x), (len(x), 1)),
extra_features)
print type(title_corpus)
print title_corpus.shape
title_pca = clone(pca)
title_pca.set_params(n_components=200)
title_corpus_pca = title_pca.fit_transform(title_corpus)
print type(title_corpus_pca)
else:
type_n = "train"
type_v = "valid"
vectorizer = CountVectorizer(
max_features=200,
)
short_id = "count_200f"
tfidf_columns = ["Title", "FullDescription", "LocationRaw"]
#dio.make_counts(vectorizer, short_id, tfidf_columns, type_n, type_v)
columns = ["Category", "ContractTime", "ContractType"]
le_features = dio.get_le_features(columns, "train_full")
extra_features = dio.get_features(columns, type_n, le_features)
extra_valid_features = dio.get_features(columns, type_v, le_features)
#features = dio.join_features("%s_" + type_n + "_count_vector_matrix_max_f_200",
#["Title", "FullDescription", "LocationRaw"],
#extra_features)
#validation_features = dio.join_features("%s_" + type_v + "_count_vector_matrix_max_f_200",
#["Title", "FullDescription", "LocationRaw"],
#extra_valid_features).astype(np.int64)
features = dio.join_features("%s_" + type_n + "_" + short_id + "_matrix",
tfidf_columns,
extra_features)
validation_features = dio.join_features("%s_" + type_v + "_" + short_id + "_matrix",
tfidf_columns,
extra_valid_features)
from data_io import DataIO
from sklearn.decomposition import RandomizedPCA
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.base import clone
from sklearn.cross_validation import cross_val_score
import numpy as np
dio = DataIO("Settings.json")
title_corpus = dio.read_gensim_corpus("train_title_nltk_filtered.corpus.mtx")
pca = RandomizedPCA(random_state=3465343)
salaries = dio.get_salaries("train", log=True)
columns = ["Category", "ContractTime", "ContractType"]
le_features = dio.get_le_features(columns, "train_full")
extra_features = dio.get_features(columns, "train", le_features)
#extra_valid_features = dio.get_features(columns, "valid", le_features)
param = "RandomizedPCA title 200 Fulldescription 200 " + ",".join(columns)
print map(len, extra_features)
extra_features = map(lambda x: np.reshape(np.array(x),(len(x),1)),extra_features)
print type(title_corpus)
print title_corpus.shape
title_pca = clone(pca)
title_pca.set_params(n_components=200)
title_corpus_pca = title_pca.fit_transform(title_corpus)