s444519/retroc2
1
0
Fork 0
forked from kubapok/retroc2
Code Issues Pull Requests Projects Releases Wiki Activity

Compare commits

merge into: s444519:my-brilliant-branch
Branches Tags
s444519:master
s444519:my-brilliant-branch
kubapok:master
...
pull from: s444519:master
Branches Tags
s444519:my-brilliant-branch
s444519:master
kubapok:master

No commits in common. "my-brilliant-branch" and "master" have entirely different histories.
my-brillia ... master

4 changed files with 0 additions and 34365 deletions
Show Stats Expand all files Collapse all files

3
.gitignore vendored
View File

@ -1,3 +0,0 @@
*~
*.swp
*.o

20000
dev-0/out.tsv
View File

File diff suppressed because it is too large Load Diff

142
foo.py
View File

@ -1,142 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# In[24]:
import pandas as pd
import numpy as np
import math
from sklearn.pipeline import make_pipeline
import os
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import csv
# In[39]:
train = pd.read_csv('train/train.tsv', header=None, sep='\t')
dev_x0 = pd.read_csv('dev-0/in.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
dev_y0 = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t',quoting=csv.QUOTE_NONE, error_bad_lines=False)
dev_x1 = pd.read_csv('dev-1/in.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
dev_y1 = pd.read_csv('dev-1/expected.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
test_x = pd.read_csv('test-A/in.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
# In[26]:
len(dev_y0[0])
# In[27]:
len(dev_x0[0])
# In[40]:
len(dev_y1[0])
# In[41]:
len(dev_x1[0])
# In[43]:
train_x = train[4]
train_y_mean = (train.iloc[:, 0] + train.iloc[:, 1])/2
# In[49]:
train_y_mean = train_y_mean[:30000]
train_x = train_x[:30000]
# In[51]:
vectorizer = TfidfVectorizer()
X_train_tfidf = vectorizer.fit_transform(train_x)
# In[52]:
lm = LinearRegression()
lm.fit(X_train_tfidf,train_y_mean)
X_dev0_= vectorizer.transform(dev_x0[0])
X_dev1_ = vectorizer.transform(dev_x1[0])
X_test_ = vectorizer.transform(test_x[0])
# In[54]:
dev0_y_pred = lm.predict(X_dev0_)
dev1_y_pred = lm.predict(X_dev1_)
test_y_pred = lm.predict(X_test_)
# In[55]:
print(dev_y0[:19998])
# In[58]:
rmse_dev0 = mean_squared_error(dev_y0, dev0_y_pred, squared=False)
rmse_dev1 = mean_squared_error(dev_y1,dev1_y_pred, squared = False)
print(rmse_dev0, rmse_dev1)
# In[18]:
print(dev_y0[:10])
# In[64]:
type(dev0_y_pred)
# In[65]:
np.savetxt("out.tsv",dev0_y_pred, delimiter="\t", fmt='%1.8f')
# In[66]:
np.savetxt("out.tsv",dev1_y_pred, delimiter="\t", fmt='%1.8f')
# In[67]:
np.savetxt("out.tsv",test_y_pred, delimiter="\t", fmt='%1.8f')
# In[ ]:

14220
test-A/out.tsv
View File

File diff suppressed because it is too large Load Diff