s460936/retroc2
1
0
Fork 0
forked from kubapok/retroc2
Code Issues Pull Requests Projects Releases Wiki Activity

Secon stage

Browse Source
This commit is contained in:
kociuba 2021-04-27 20:51:28 +02:00
parent 44375fa02b
commit fa5e5e599e
3 changed files with 19859 additions and 4863 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24696
dev-0/out.tsv
View File

File diff suppressed because it is too large Load Diff

BIN
geval Executable file
View File

Binary file not shown.

24
mian.py
View File

@ -1,3 +1,5 @@
import csv
import gensim as gensim import gensim as gensim
import smart_open import smart_open
from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.feature_extraction.text import TfidfVectorizer
@ -11,30 +13,21 @@ import pandas as pd
def read_train_file(inDirectory): def read_train_file(inDirectory):
colnames = ['start_date', 'end_date', 'title', 'sort_title', 'data'] colnames = ['start_date', 'end_date', 'title', 'sort_title', 'data']
df_train = pd.read_csv(inDirectory, sep="\t", names=colnames) df_train = pd.read_csv(inDirectory, sep="\t", names=colnames)
return df_train[:5000] return df_train[:tain_set]
def read_evaluate_file(inDirectory): def read_evaluate_file(inDirectory):
colnames = ['data'] colnames = ['data']
df_train = pd.read_csv(inDirectory, sep="\t", names=colnames) df_train = pd.read_csv(inDirectory, sep="\t", names=colnames, quoting=csv.QUOTE_NONE, error_bad_lines=False)
return df_train[:5000] return df_train
def train_date_mean(df): def train_date_mean(df):
date_mean = (df['start_date'] + df['end_date']) / 2 date_mean = (df['start_date'] + df['end_date']) / 2
return date_mean return date_mean
def preper_data(df): tain_set = 50000
document_list = list()
for line in df:
tokens = gensim.utils.simple_preprocess(line, min_len=2, max_len=15)
filtered_sentence = []
for word in tokens:
if word not in get_stop_words('polish'):
filtered_sentence.append(word)
document_list.append(filtered_sentence)
return document_list
df = read_train_file('train/train.tsv') df = read_train_file('train/train.tsv')
date_mean_df = train_date_mean(df)[:5000] date_mean_df = train_date_mean(df)
vectorizer = TfidfVectorizer(stop_words=get_stop_words('polish')) vectorizer = TfidfVectorizer(stop_words=get_stop_words('polish'))
train_vectorized_corpus = vectorizer.fit_transform(df['data']) train_vectorized_corpus = vectorizer.fit_transform(df['data'])
reg = LinearRegression().fit(train_vectorized_corpus, date_mean_df) reg = LinearRegression().fit(train_vectorized_corpus, date_mean_df)
@ -45,3 +38,6 @@ evaluate = reg.predict(evaluate_vectorized_corpus)
with open("dev-0/out.tsv", 'w') as file: with open("dev-0/out.tsv", 'w') as file:
for e in evaluate: for e in evaluate:
file.write("%i\n" % e) file.write("%i\n" % e)
os.system("./geval -t dev-0")