From 38911e69e59379f11ada33925ac6b00aad5c449f Mon Sep 17 00:00:00 2001
From: Damian Bregier <dambre@st.amu.edu.pl>
Date: Tue, 25 May 2021 23:57:06 +0200
Subject: [PATCH] ADD: Model file

---
 regression.py | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 84 insertions(+)
 create mode 100644 regression.py

diff --git a/regression.py b/regression.py
new file mode 100644
index 0000000..6eece22
--- /dev/null
+++ b/regression.py
@@ -0,0 +1,84 @@
+import numpy as np
+import pandas as pd
+import torch
+from csv import QUOTE_NONE
+from nltk.tokenize import word_tokenize
+import gensim.downloader
+
+#Based on source material from classes
+class MyNeuralNetwork(torch.nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(MyNeuralNetwork, self).__init__()
+        self.fc1 = torch.nn.Linear(input_size, hidden_size)
+        self.fc2 = torch.nn.Linear(hidden_size, num_classes)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = torch.relu(x)
+        x = self.fc2(x)
+        x = torch.sigmoid(x)
+        return x
+
+word2vec = gensim.downloader.load('word2vec-google-news-300')
+def get_word2vec(document):
+    return np.mean([word2vec[token] for token in document if token in word2vec] or [np.zeros(300)], axis=0)
+
+#Basic paths + reading from files
+XtrainingData = pd.read_table('train/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['content', 'id'])
+YtrainingData = pd.read_table('train/expected.tsv', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['label'])['label']
+XtestData = pd.read_table('test-A/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['content', 'id'])
+XdevData = pd.read_table('dev-0/in.tsv.xz', error_bad_lines=False, header=None, quoting=QUOTE_NONE, names=['content', 'id'])
+
+
+#Data filltering and preprocessing
+XtrainingData = [word_tokenize(row) for row in XtrainingData['content'].str.lower()]
+XtestData = [word_tokenize(row) for row in XtestData['content'].str.lower()]
+XdevData = [word_tokenize(row) for row in XdevData['content'].str.lower()]
+XtrainingData = [get_word2vec(document) for document in XtrainingData]
+XtestData = [get_word2vec(document) for document in XtestData]
+XdevData = [get_word2vec(document) for document in XdevData]
+
+#Basic parameters for the model
+eph = 30
+batches = 5
+network = MyNeuralNetwork(300, 600, 1)
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.SGD(network.parameters(), lr=0.02)
+
+#Model training according to source files from classes
+for epoch in range(eph):
+    network.train()
+    for i in range(0, YtrainingData.shape[0], batches):
+        x = XtrainingData[i :i + batches]
+        x = torch.tensor(x)
+        y = YtrainingData[i :i + batches]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+
+        outputs = network(x.float())
+        loss = criterion(outputs, y)
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+#Basic evaluation
+YpredDev = []
+YtestPred = []
+
+with torch.no_grad():
+    for i in range(0, len(XdevData), batches):
+        x = XdevData[i :i + batches]
+        x = torch.tensor(x)
+        outputs = network(x.float())
+        prediction = outputs > 0.5
+        YpredDev += prediction.tolist()
+
+    for i in range(0, len(XtestData), batches):
+        x = XtestData[i :i + batches]
+        x = torch.tensor(x)
+        outputs = network(x.float())
+        prediction = outputs > 0.5
+        YtestPred += prediction.tolist()
+
+#Saving outputs
+np.asarray(YpredDev, dtype=np.int32).tofile('./dev-0/out.tsv', sep='\n')
+np.asarray(YtestPred, dtype=np.int32).tofile('./test-A/out.tsv', sep='\n')