Test

Naiwny_bayes.ipynb

@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sklearn\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "import numpy as np\n",
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "from sklearn.preprocessing import LabelEncoder "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def getInput(path):\n",
+    "    with open(path,encoding='utf-8') as f:\n",
+    "          return f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/c/Users/mkoci/Desktop/naiwny_bayes\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pwd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_in=getInput('./train/in.tsv')\n",
+    "train_expected=getInput('./train/expected.tsv')\n",
+    "test_in=getInput('./test-A/in.tsv')\n",
+    "dev_in=getInput('./dev-0/in.tsv')\n",
+    "dev_expected=getInput('./dev-0/expected.tsv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())\n",
+    "encTransform = LabelEncoder().fit_transform(train_expected)\n",
+    "model = pipeline.fit(train_in, encTransform)\n",
+    "dev_predicted = model.predict(dev_in)\n",
+    "test_predicted = model.predict(test_in)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('./dev-0/out.tsv', \"w\") as result:\n",
+    "            for out in dev_predicted:\n",
+    "                result.write(str(out) + '\\n')\n",
+    "with open('./test-A/out.tsv', \"w\") as result:\n",
+    "            for out in test_predicted:\n",
+    "                result.write(str(out) + '\\n')                "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[NbConvertApp] Converting notebook Naiwny_bayes.ipynb to script\n",
+      "[NbConvertApp] Writing 1337 bytes to Naiwny_bayes.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "!jupyter nbconvert --to script Naiwny_bayes.ipynb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

Naiwny_bayes.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[46]:
+
+
+import sklearn
+from sklearn.pipeline import make_pipeline
+from sklearn.feature_extraction.text import TfidfVectorizer
+import numpy as np
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.preprocessing import LabelEncoder 
+
+
+# In[47]:
+
+
+def getInput(path):
+    with open(path,encoding='utf-8') as f:
+          return f.readlines()
+
+
+# In[48]:
+
+
+get_ipython().system('pwd')
+
+
+# In[49]:
+
+
+train_in=getInput('./train/in.tsv')
+train_expected=getInput('./train/expected.tsv')
+test_in=getInput('./test-A/in.tsv')
+dev_in=getInput('./dev-0/in.tsv')
+dev_expected=getInput('./dev-0/expected.tsv')
+
+
+# In[50]:
+
+
+pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())
+encTransform = LabelEncoder().fit_transform(train_expected)
+model = pipeline.fit(train_in, encTransform)
+dev_predicted = model.predict(dev_in)
+test_predicted = model.predict(test_in)
+
+
+# In[ ]:
+
+
+
+
+
+# In[54]:
+
+
+with open('./dev-0/out.tsv', "w") as result:
+            for out in dev_predicted:
+                result.write(str(out) + '\n')
+with open('./test-A/out.tsv', "w") as result:
+            for out in test_predicted:
+                result.write(str(out) + '\n')                
+
+
+# In[55]:
+
+
+get_ipython().system('jupyter nbconvert --to script Naiwny_bayes.ipynb')
+
+
+# In[ ]:
+
+
+
+

Untitled.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def getInput(path):\n",
+    "    with open(path,encoding='utf-8') as f:\n",
+    "          return f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gensim.downloader as gensim\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import torch\n",
+    "from nltk.tokenize import word_tokenize"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "word2vec = gensim.load('word2vec-google-news-300')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# train_in=getInput('./train/in.tsv')\n",
+    "# train_expected=getInput('./train/expected.tsv')\n",
+    "# test_in=getInput('./test-A/in.tsv')\n",
+    "# dev_in=getInput('./dev-0/in.tsv')\n",
+    "# dev_expected=getInput('./dev-0/expected.tsv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class NeuralNetworkModel(torch.nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(NeuralNetworkModel, self).__init__()\n",
+    "        self.l01 = torch.nn.Linear(300, 300)\n",
+    "        self.l02 = torch.nn.Linear(300, 1)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.l01(x)\n",
+    "        x = torch.relu(x)\n",
+    "        x = self.l02(x)\n",
+    "        x = torch.sigmoid(x)\n",
+    "        return x\n",
+    "\n",
+    "def d2v(doc):\n",
+    "    return np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(300)], axis=0)\n",
+    "x_train = pd.read_table('train/in.tsv.xz', compression='xz', sep='\\t', header=None, error_bad_lines=False, quoting=3)\n",
+    "x_train = x_train[0].str.lower()\n",
+    "x_dev = pd.read_table('dev-0/in.tsv.xz', compression='xz', sep='\\t', header=None, quoting=3)\n",
+    "x_dev = x_dev[0].str.lower()\n",
+    "x_test = pd.read_table('test-A/in.tsv.xz', compression='xz', sep='\\t', header=None, quoting=3)\n",
+    "x_test = x_test[0].str.lower()\n",
+    "y_train = pd.read_table('train/expected.tsv', sep='\\t', header=None, quoting=3)\n",
+    "y_train = y_train[0]\n",
+    "x_train = [word_tokenize(x) for x in x_train]\n",
+    "x_dev = [word_tokenize(x) for x in x_dev]\n",
+    "x_test = [word_tokenize(x) for x in x_test]\n",
+    "x_train = [d2v(doc) for doc in x_train]\n",
+    "x_dev = [d2v(doc) for doc in x_dev]\n",
+    "x_test = [d2v(doc) for doc in x_test]\n",
+    "model = NeuralNetworkModel()\n",
+    "BATCH_SIZE = 10\n",
+    "criterion = torch.nn.BCELoss()\n",
+    "optimizer = torch.optim.Adam(model.parameters())\n",
+    "for epoch in range(BATCH_SIZE):\n",
+    "    model.train()\n",
+    "    for i in range(0, y_train.shape[0], BATCH_SIZE):\n",
+    "        X = x_train[i:i + BATCH_SIZE]\n",
+    "        X = torch.tensor(X)\n",
+    "        y = y_train[i:i + BATCH_SIZE]\n",
+    "        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)\n",
+    "        optimizer.zero_grad()\n",
+    "        outputs = model(X.float())\n",
+    "        loss = criterion(outputs, y)\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "y_dev = []\n",
+    "y_test = []\n",
+    "model.eval()\n",
+    "with torch.no_grad():\n",
+    "    for i in range(0, len(x_dev), BATCH_SIZE):\n",
+    "        X = x_dev[i:i + BATCH_SIZE]\n",
+    "        X = torch.tensor(X)\n",
+    "        outputs = model(X.float())\n",
+    "        y = (outputs > 0.5)\n",
+    "        y_dev.extend(y)\n",
+    "\n",
+    "    for i in range(0, len(x_test), BATCH_SIZE):\n",
+    "        X = x_test[i:i + BATCH_SIZE]\n",
+    "        X = torch.tensor(X)\n",
+    "        outputs = model(X.float())\n",
+    "        y = (outputs >= 0.5)\n",
+    "        y_test.extend(y)\n",
+    "\n",
+    "y_dev = np.asarray(y_dev, dtype=np.int32)\n",
+    "Y_dev = pd.DataFrame({'label': y_dev})\n",
+    "y_test = np.asarray(y_test, dtype=np.int32)\n",
+    "Y_test = pd.DataFrame({'label': y_test})\n",
+    "Y_dev.to_csv(r'dev-0/out.tsv', sep='\\t', index=False, header=False)\n",
+    "Y_test.to_csv(r'test-A/out.tsv', sep='\\t', index=False, header=False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

Untitled.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[2]:
+
+
+def getInput(path):
+    with open(path,encoding='utf-8') as f:
+          return f.readlines()
+
+
+# In[6]:
+
+
+import gensim.downloader as gensim
+import numpy as np
+import pandas as pd
+import torch
+from nltk.tokenize import word_tokenize
+
+
+# In[8]:
+
+
+word2vec = gensim.load('word2vec-google-news-300')
+
+
+# In[5]:
+
+
+# train_in=getInput('./train/in.tsv')
+# train_expected=getInput('./train/expected.tsv')
+# test_in=getInput('./test-A/in.tsv')
+# dev_in=getInput('./dev-0/in.tsv')
+# dev_expected=getInput('./dev-0/expected.tsv')
+
+
+# In[14]:
+
+
+class NeuralNetworkModel(torch.nn.Module):
+    def __init__(self):
+        super(NeuralNetworkModel, self).__init__()
+        self.l01 = torch.nn.Linear(300, 300)
+        self.l02 = torch.nn.Linear(300, 1)
+
+    def forward(self, x):
+        x = self.l01(x)
+        x = torch.relu(x)
+        x = self.l02(x)
+        x = torch.sigmoid(x)
+        return x
+
+def d2v(doc):
+    return np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(300)], axis=0)
+x_train = pd.read_table('train/in.tsv.xz', compression='xz', sep='\t', header=None, error_bad_lines=False, quoting=3)
+x_train = x_train[0].str.lower()
+x_dev = pd.read_table('dev-0/in.tsv.xz', compression='xz', sep='\t', header=None, quoting=3)
+x_dev = x_dev[0].str.lower()
+x_test = pd.read_table('test-A/in.tsv.xz', compression='xz', sep='\t', header=None, quoting=3)
+x_test = x_test[0].str.lower()
+y_train = pd.read_table('train/expected.tsv', sep='\t', header=None, quoting=3)
+y_train = y_train[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]
+x_train = [d2v(doc) for doc in x_train]
+x_dev = [d2v(doc) for doc in x_dev]
+x_test = [d2v(doc) for doc in x_test]
+model = NeuralNetworkModel()
+BATCH_SIZE = 10
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.Adam(model.parameters())
+for epoch in range(BATCH_SIZE):
+    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)
+        optimizer.zero_grad()
+        outputs = model(X.float())
+        loss = criterion(outputs, y)
+        loss.backward()
+        optimizer.step()
+y_dev = []
+y_test = []
+model.eval()
+with torch.no_grad():
+    for i in range(0, len(x_dev), BATCH_SIZE):
+        X = x_dev[i:i + BATCH_SIZE]
+        X = torch.tensor(X)
+        outputs = model(X.float())
+        y = (outputs > 0.5)
+        y_dev.extend(y)
+
+    for i in range(0, len(x_test), BATCH_SIZE):
+        X = x_test[i:i + BATCH_SIZE]
+        X = torch.tensor(X)
+        outputs = model(X.float())
+        y = (outputs >= 0.5)
+        y_test.extend(y)
+
+y_dev = np.asarray(y_dev, dtype=np.int32)
+Y_dev = pd.DataFrame({'label': y_dev})
+y_test = np.asarray(y_test, dtype=np.int32)
+Y_test = pd.DataFrame({'label': y_test})
+Y_dev.to_csv(r'dev-0/out.tsv', sep='\t', index=False, header=False)
+Y_test.to_csv(r'test-A/out.tsv', sep='\t', index=False, header=False)
+
+
+# In[ ]:
+
+
+
+

Untitled10-Copy1.py

@@ -0,0 +1,222 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+import csv
+
+
+# In[2]:
+
+
+get_ipython().system('pip install gensim')
+
+
+# In[17]:
+
+
+import nltk
+nltk.download('punkt')
+
+
+# In[9]:
+
+
+get_ipython().system('pip install nltk')
+
+
+# In[3]:
+
+
+get_ipython().system('pip install torch')
+
+
+# In[4]:
+
+
+import gensim.downloader
+import numpy as np
+import pandas as pd
+import torch
+
+
+# In[5]:
+
+
+import torch.nn as nn
+from nltk import word_tokenize
+
+
+# In[13]:
+
+
+header_names = ["content", "id", "label"]
+
+
+# In[23]:
+
+
+class FF(nn.Module):
+    def __init__(self, input_dim, hidden_dim, output_dim):
+        super(FF, self).__init__()
+        self.fc1 = nn.Linear(input_dim, hidden_dim)
+        self.relu1 = nn.ReLU()
+        self.fc2 = nn.Linear(hidden_dim, hidden_dim)
+        self.relu2 = nn.ReLU()
+        self.fc3 = nn.Linear(hidden_dim, output_dim)
+
+    def forward(self, x):
+        out = self.fc1(x)
+        out = self.relu1(out)
+        out = self.relu2(out)
+        out = self.fc3(out)
+        return torch.sigmoid(out)
+
+train_set_labels = pd.read_table(
+    "train/expected.tsv",
+    error_bad_lines=False,
+    quoting=csv.QUOTE_NONE,
+    header=None,
+    names=header_names[2:],
+)
+
+train_set_features = pd.read_table(
+    "train/in.tsv.xz",
+    error_bad_lines=False,
+    quoting=csv.QUOTE_NONE,
+    header=None,
+    names=header_names[:2],
+)
+
+
+test_set = pd.read_table(
+    "test-A/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    names=header_names[:2],
+)
+
+dev_set = pd.read_table(
+    "dev-0/in.tsv.xz",
+    error_bad_lines=False,
+    header=None,
+    quoting=csv.QUOTE_NONE,
+    names=header_names[:2],
+)
+X_train = train_set_features["content"].str.lower()
+y_train = train_set_labels["label"]
+
+X_dev = dev_set["content"].str.lower()
+X_test = test_set["content"].str.lower()
+X_train = [word_tokenize(content) for content in X_train]
+X_dev = [word_tokenize(content) for content in X_dev]
+X_test = [word_tokenize(content) for content in X_test]
+word2vec = gensim.downloader.load("word2vec-google-news-300")
+
+
+# In[24]:
+
+
+X_train = [
+    np.mean(
+        [word2vec[word] for word in content if word in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+    for content in X_train
+]
+X_dev = [
+    np.mean(
+        [word2vec[word] for word in content if word in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+    for content in X_dev
+]
+
+X_test = [
+    np.mean(
+        [word2vec[word] for word in content if word in word2vec] or [np.zeros(300)],
+        axis=0,
+    )
+    for content in X_test
+]
+hidden_layer = 650
+epochs = 15
+batch_size = 10
+
+
+# In[27]:
+
+
+output_dim = 1
+
+
+input_dim =300
+model = FF(input_dim, hidden_layer, output_dim)
+optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
+criterion = torch.nn.BCELoss()
+
+
+# In[28]:
+
+
+for epoch in range(epochs):
+    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)
+
+        outputs = model(X.float())
+        loss = criterion(outputs, y)
+
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+test_prediction = []
+dev_prediction = []
+model.eval()
+with torch.no_grad():
+    for i in range(0, len(X_test), batch_size):
+        X = X_test[i : i + batch_size]
+        X = torch.tensor(X)
+
+        outputs = model(X.float())
+
+        prediction = outputs > 0.5
+        test_prediction += prediction.tolist()
+
+    for i in range(0, len(X_dev), batch_size):
+        X = X_dev[i : i + batch_size]
+        X = torch.tensor(X)
+
+        outputs = model(X.float())
+
+        prediction = outputs > 0.5
+        dev_prediction += prediction.tolist()
+
+test_prediction = np.asarray(test_prediction, dtype=np.int32)
+dev_prediction = np.asarray(dev_prediction, dtype=np.int32)
+test_prediction.tofile("./test-A/out.tsv", sep="\n")
+dev_prediction.tofile("./dev-0/out.tsv", sep="\n")
+
+
+# In[ ]:
+
+
+
+
+
+# In[ ]:
+
+
+
+
+
+# In[ ]:
+
+
+
+