s444417/s444417-paranormal-or-skeptic-ISI-public
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

add python script

Browse Source
This commit is contained in:
s444417 2022-05-11 00:19:40 +02:00
parent 15eee7e200
commit b55ac8b880
1 changed files with 74 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

84
run.py
View File

@ -1,22 +1,84 @@
# %%
import lzma import lzma
import sys import sys
from io import StringIO from io import StringIO
from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd import pandas as pd
import numpy
pathX = "./train/in.tsv.xz" pathX = "./train/in.tsv.xz"
# pathX = "./train/in.tsv"
pathY = "./train/expected.tsv" pathY = "./train/expected.tsv"
nrows = 10000
data = lzma.open(pathX, mode='rt', encoding='utf-8').read() # %%
stringIO = StringIO(data) # data = lzma.open(pathX, mode='rt', encoding='utf-8').read()
df = pd.read_csv(stringIO, sep="\t", header=None) # stringIO = StringIO(data)
df = df.drop(df.columns[[1]], axis=1) # df = pd.read_csv(stringIO, sep="\t", header=None)
topics = pd.read_csv(pathY, sep='\t', header=None) df = pd.read_csv(pathX, sep='\t', nrows=nrows, header=None)
df = df.drop(df.columns[1], axis=1)
topics = pd.read_csv(pathY, sep='\t', nrows=nrows, header=None)
vectorizer = TfidfVectorizer() # %%
print(len(df.index))
print(len(topics.index))
# %%
df.sample()
# %%
vectorizer = TfidfVectorizer(lowercase=True, stop_words=['english'])
X = vectorizer.fit_transform(df.to_numpy().ravel()) X = vectorizer.fit_transform(df.to_numpy().ravel())
print(vectorizer.get_feature_names_out()) vectorizer.get_feature_names_out()
# %%
# vectorizer.transform("Ala ma kotka".lower().split())
# %%
df = df.reset_index()
# %%
tfidfVector = vectorizer.transform(df[0])
# %%
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
gnb.fit(tfidfVector.todense(), topics)
# %%
testXPath = "./dev-0/in.tsv.xz"
testYPath = "./dev-0/expected.tsv"
testX = pd.read_csv(testXPath, sep='\t', nrows=nrows, header=None)
testY = pd.read_csv(testYPath, sep='\t', nrows=nrows, header=None)
testXtfidfVector = vectorizer.transform(testX[0])
# %%
testXPath = "./test-A/in.tsv.xz"
testYPath = "./test-A/expected.tsv"
testX = pd.read_csv(testXPath, sep='\t', nrows=nrows, header=None)
# testY = pd.read_csv(testYPath, sep='\t', nrows=nrows, header=None)
testXtfidfVector = vectorizer.transform(testX[0])
# %%
pred = gnb.predict(testXtfidfVector.todense())
print(pred)
import csv
with open(testYPath, 'w', newline='') as f_output:
tsv_output = csv.writer(f_output, delimiter='\n')
tsv_output.writerow(pred)