Compare commits

..

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

4 changed files with 0 additions and 10889 deletions

File diff suppressed because it is too large Load Diff

160
foo.py
View File

@ -1,160 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# In[3]:
import pathlib
from collections import Counter
from sklearn.metrics import *
import pandas as pd
# In[1]:
import numpy as np, pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
from sklearn.metrics import confusion_matrix, accuracy_score
sns.set() # use seaborn plotting style
# In[5]:
train_x = pd.read_csv('train/in.tsv', header=None, sep='\t')
train_y = pd.read_csv('train/expected.tsv', header=None, sep='\t')
dev_x = pd.read_csv('dev-0/in.tsv', header=None, sep='\t')
dev_y = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t')
test_x = pd.read_csv('test-A/in.tsv', header=None, sep='\t')
# In[61]:
print(dev_y.shape)
print(dev_x.shape)
# In[11]:
print(train_x[:15])
# In[27]:
print(train_x.shape)
# In[49]:
print(train_y.shape)
# In[8]:
print(train_y[:15])
# In[53]:
print(dev_x[:4])
# In[119]:
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
vec = CountVectorizer(stop_words='english')
x1 = vec.fit_transform(train_x[:20000][0])
tfidf_transformer = TfidfTransformer()
x1_tf = tfidf_transformer.fit_transform(x1)
# In[120]:
# Build the model
#model = make_pipeline(TfidfVectorizer(), MultinomialNB())
clf = MultinomialNB().fit(x1_tf, train_y[:20000][0])
# In[121]:
# Train the model using the training data
#model.fit(x1[:][0], train_y[:289541][0])
# Predict the categories of the test data
X_new_counts = vec.transform(dev_x[:][0])
# We call transform instead of fit_transform because it's already been fit
X_new_tfidf = tfidf_transformer.transform(X_new_counts)
#predicted_categories = model.predict(dev_x[:][0])
# In[122]:
predicted = clf.predict(X_new_tfidf)
# In[125]:
print(predicted[:10])
# In[126]:
print(predicted.shape)
# In[123]:
#mat = confusion_matrix(dev_y[:][0],predicted_categories)
print("The accuracy is {}".format(accuracy_score( dev_y[:][0],predicted_categories)))
# In[124]:
print('We got an accuracy of',np.mean(predicted == dev_y[:][0])*100, '% over the test data.')
# In[130]:
np.savetxt("out.tsv",predicted, delimiter="\t", fmt='%d')
# In[131]:
X_test = vec.transform(test_x[:][0])
# We call transform instead of fit_transform because it's already been fit
X_tfidf_test = tfidf_transformer.transform(X_test)
predicted_test = clf.predict(X_tfidf_test)
np.savetxt("out.tsv",predicted_test, delimiter="\t", fmt='%d')
# In[ ]:

View File

@ -1,305 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# In[3]:
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_20newsgroups
# https://scikit-learn.org/0.19/datasets/twenty_newsgroups.html
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics import accuracy_score
# In[71]:
import numpy as np
import gensim
import torch
import pandas as pd
from gensim.test.utils import common_texts
from gensim.models import Word2Vec
import csv
# In[84]:
train_x = pd.read_csv('train/in.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
train_y = pd.read_csv('train/expected.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
dev_x = pd.read_csv('dev-0/in.tsv', header=None, sep='\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)
dev_y = pd.read_csv('dev-0/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[85]:
print(len(train_x))
# In[86]:
print(len(train_y))
# In[87]:
train_y = train_y[0]
# In[100]:
dev_y = dev_y[0]
# In[88]:
print(type(train_y))
# In[89]:
train_y = train_y.to_numpy()
# In[102]:
dev_y = dev_y.to_numpy()
# In[90]:
train_x.head
# In[91]:
dev_x.head()
# In[92]:
train_x = train_x[0]
# In[93]:
vec_model = Word2Vec(train_x, vector_size=100, window=5, min_count=1, workers=4)
# In[ ]:
def w2v(model, data):
return np.array([np.mean([model.wv[word] if word in model.wv.key_to_index else np.zeros(100, dtype=float) for word in doc], axis=0) for doc in data])
# In[ ]:
w2v()
# In[96]:
dev_x = dev_x[0]
test_x = test_x[0]
# In[95]:
vec_x_train = np.array([np.mean([vec_model.wv[word] if word in vec_model.wv.key_to_index else np.zeros(100, dtype=float) for word in doc], axis=0) for doc in train_x])
# In[97]:
vec_x_dev = np.array([np.mean([vec_model.wv[word] if word in vec_model.wv.key_to_index else np.zeros(100, dtype=float) for word in doc], axis=0) for doc in dev_x])
vec_x_test = np.array([np.mean([vec_model.wv[word] if word in vec_model.wv.key_to_index else np.zeros(100, dtype=float) for word in doc], axis=0) for doc in test_x])
# In[36]:
X_dev0_w2v = vectorize(vec_model,dev_x)
X_test_w2v = vectorize(vec_model,test_x)
# In[7]:
class NeuralNetworkModel(torch.nn.Module):
def __init__(self):
super(NeuralNetworkModel, self).__init__()
self.fc1 = torch.nn.Linear(FEAUTERES,500)
self.fc2 = torch.nn.Linear(500,1)
def forward(self, x):
x = self.fc1(x)
x = torch.relu(x)
x = self.fc2(x)
x = torch.sigmoid(x)
return x
# In[37]:
criterion = torch.nn.BCELoss()
optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.1)
# In[8]:
def get_loss_acc(model, X_dataset, Y_dataset):
loss_score = 0
acc_score = 0
items_total = 0
model.eval()
for i in range(0, Y_dataset.shape[0], BATCH_SIZE):
X = np.array(X_dataset[i:i+BATCH_SIZE]).astype(np.float32)
X = torch.tensor(X)
Y = Y_dataset[i:i+BATCH_SIZE]
Y = torch.tensor(Y.astype(np.float32)).reshape(-1,1)
Y_predictions = model(X)
acc_score += torch.sum((Y_predictions > 0.5) == Y).item()
items_total += Y.shape[0]
loss = criterion(Y_predictions, Y)
loss_score += loss.item() * Y.shape[0]
return (loss_score / items_total), (acc_score / items_total)
# In[9]:
def predict(model, data):
model.eval()
predictions = []
for x in data:
X = torch.tensor(np.array(x).astype(np.float32))
Y_predictions = model(X)
if Y_predictions[0] > 0.5:
predictions.append("1")
else:
predictions.append("0")
return predictions
# In[18]:
FEAUTERES = 100
# In[62]:
BATCH_SIZE = 5
# In[58]:
nn_model = NeuralNetworkModel()
# In[103]:
for epoch in range(7):
loss_score = 0
acc_score = 0
items_total = 0
nn_model.train()
for i in range(0, train_y.shape[0], BATCH_SIZE):
X = vec_x_train[i:i+BATCH_SIZE]
X = torch.tensor(X)
Y = train_y[i:i+BATCH_SIZE]
Y = torch.tensor(Y.astype(np.float32)).reshape(-1,1)
Y_predictions = nn_model(X)
acc_score += torch.sum((Y_predictions > 0.5) == Y).item()
items_total += Y.shape[0]
optimizer.zero_grad()
loss = criterion(Y_predictions, Y)
loss.backward()
optimizer.step()
loss_score += loss.item() * Y.shape[0]
display(epoch)
display(get_loss_acc(nn_model,vec_x_train, train_y))
display(get_loss_acc(nn_model, vec_x_dev, dev_y))
# In[104]:
dev_pred = predict(nn_model, vec_x_dev)
test_pred = predict(nn_model, vec_x_test)
# In[105]:
dev_pred
# In[119]:
dev_pred = [int(i) for i in dev_pred]
test_pred = [int(i) for i in test_pred]
# In[120]:
dev_pred = np.array(dev_pred)
test_pred = np.array(test_pred)
# In[117]:
dev_pred
# In[121]:
np.savetxt("dev-0/out.tsv",dev_pred, delimiter="\t", fmt='%d')
# In[122]:
np.savetxt("test-A/out.tsv",test_pred, delimiter="\t", fmt='%d')
# In[ ]:

File diff suppressed because it is too large Load Diff