pretty please

paranormal_or_skeptic.py

@@ -0,0 +1,109 @@
+
+from nltk.util import pr
+import pandas as pd
+import numpy as np
+import torch
+from gensim import downloader
+from nltk.tokenize import word_tokenize
+import csv
+
+BATCH_SIZE = 5
+
+
+class NeuralNetworkModel(torch.nn.Module):
+
+    def __init__(self):
+        dim = 200
+        super(NeuralNetworkModel, self).__init__()
+        self.one = torch.nn.Linear(dim, 500)
+        self.two = torch.nn.Linear(500, 1)
+
+    def forward(self, x):
+        x = self.one(x)
+        x = torch.relu(x)
+        x = self.two(x)
+        x = torch.sigmoid(x)
+        return x
+
+
+def read_data():
+    x_labels = (pd.read_csv('in-header.tsv', sep='\t')).columns
+    y_labels = (pd.read_csv('out-header.tsv', sep='\t')).columns
+
+    x_train = pd.read_table('train/in.tsv', header=None, quoting=csv.QUOTE_NONE, names=x_labels)
+    y_train = pd.read_table('train/expected.tsv', header=None, quoting=csv.QUOTE_NONE, names=y_labels)
+    x_dev = pd.read_table('dev-0/in.tsv', header=None, quoting=csv.QUOTE_NONE, names=x_labels)
+    x_test = pd.read_table('test-A/in.tsv', header=None, quoting=csv.QUOTE_NONE, names=x_labels)
+
+    # remove some rows for faster development
+    remove_n = 200000
+    drop_indices = np.random.choice(x_train.index, remove_n, replace=False)
+    x_train = x_train.drop(drop_indices)
+    y_train = y_train.drop(drop_indices)
+
+    return x_labels, y_labels, x_train, y_train, x_dev, x_test
+
+
+def process_data(x_labels, y_labels, x_train, y_train, x_dev, x_test):
+    x_train = x_train[x_labels[0]].str.lower()
+    x_dev = x_dev[x_labels[0]].str.lower()
+    x_test = x_test[x_labels[0]].str.lower()
+    y_train = y_train[y_labels[0]]
+
+    x_train = [word_tokenize(x) for x in x_train]
+    x_dev = [word_tokenize(x) for x in x_dev]
+    x_test = [word_tokenize(x) for x in x_test]
+
+    w2v = downloader.load('glove-wiki-gigaword-200')
+
+    x_train = [np.mean([w2v[w] for w in d if w in w2v] or [np.zeros(200)], axis=0) for d in x_train]
+    x_dev = [np.mean([w2v[w] for w in d if w in w2v] or [np.zeros(200)], axis=0) for d in x_dev]
+    x_test = [np.mean([w2v[w] for w in d if w in w2v] or [np.zeros(200)], axis=0) for d in x_test]
+
+    return x_train, y_train, x_dev, x_test
+
+
+def predict(model, x_data, out_path):
+    y_out = []
+    model.eval()
+    with torch.no_grad():
+        for i in range(0, len(x_data), BATCH_SIZE):
+
+            x = x_data[i:i+BATCH_SIZE]
+            x = torch.tensor(x)
+            pred = nn_model(x.float())
+
+            y_pred = (pred > 0.5)
+            y_out.extend(y_pred)
+
+    y_data = np.asarray(y_out, dtype=np.int32)
+    pd.DataFrame(y_data).to_csv(out_path, sep='\t', index=False,  header=False)
+
+
+if __name__ == "__main__":
+    x_labels, y_labels, x_train, y_train, x_dev, x_test = read_data()
+
+    x_train, y_train, x_dev, x_test = process_data(x_labels, y_labels, x_train, y_train, x_dev, x_test)
+
+    nn_model = NeuralNetworkModel()
+    criterion = torch.nn.BCELoss()
+    optimizer = torch.optim.SGD(nn_model.parameters(), lr=0.1)
+
+    for epoch in range(5):
+        nn_model.train()
+
+        for i in range(0, y_train.shape[0], BATCH_SIZE):
+            X = x_train[i:i+BATCH_SIZE]
+            X = torch.tensor(X)
+            Y = y_train[i:i+BATCH_SIZE]
+            Y = torch.tensor(Y.astype(np.float32).to_numpy()).reshape(-1, 1)
+
+            Y_predictions = nn_model(X.float())
+
+            loss = criterion(Y_predictions, Y)
+            optimizer.zero_grad()
+            loss.backward()
+            optimizer.step()
+
+    predict(nn_model, x_dev, 'dev-0/out.tsv')
+    predict(nn_model, x_test, 'test-A/out.tsv')