init

.idea/TAU_21_sane_words.iml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.7" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/TAU_21_sane_words.iml" filepath="$PROJECT_DIR$/.idea/TAU_21_sane_words.iml" />
+    </modules>
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,105 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="d25a65da-2ba0-4272-a0a5-c59cbecb6088" name="Default Changelist" comment="" />
+    <option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectId" id="1UAXhosCPbReL7U2TCbyyTVGpqs" />
+  <component name="PropertiesComponent">
+    <property name="last_opened_file_path" value="$PROJECT_DIR$" />
+    <property name="settings.editor.selected.configurable" value="com.jetbrains.python.configuration.PyActiveSdkModuleConfigurable" />
+  </component>
+  <component name="RunDashboard">
+    <option name="ruleStates">
+      <list>
+        <RuleState>
+          <option name="name" value="ConfigurationTypeDashboardGroupingRule" />
+        </RuleState>
+        <RuleState>
+          <option name="name" value="StatusDashboardGroupingRule" />
+        </RuleState>
+      </list>
+    </option>
+  </component>
+  <component name="RunManager" selected="Python.solution2">
+    <configuration name="solution" type="PythonConfigurationType" factoryName="Python" temporary="true">
+      <module name="TAU_21_sane_words" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/solution.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <configuration name="solution2" type="PythonConfigurationType" factoryName="Python" temporary="true">
+      <module name="TAU_21_sane_words" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/solution2.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <recent_temporary>
+      <list>
+        <item itemvalue="Python.solution2" />
+        <item itemvalue="Python.solution" />
+      </list>
+    </recent_temporary>
+  </component>
+  <component name="SvnConfiguration">
+    <configuration />
+  </component>
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="d25a65da-2ba0-4272-a0a5-c59cbecb6088" name="Default Changelist" comment="" />
+      <created>1574800494334</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1574800494334</updated>
+    </task>
+    <servers />
+  </component>
+  <component name="XDebuggerManager">
+    <watches-manager>
+      <configuration name="PythonConfigurationType">
+        <watch expression="dev_y" />
+      </configuration>
+    </watches-manager>
+  </component>
+</project>

README.md

@@ -0,0 +1,23 @@
+
+Sane words challenge
+======================
+
+Guess if a given word is a correct Polish word in a given domain. Additionally, you have the information on reported frequency of the word in source texts.
+
+Each entry in training data set is of the form: __Sane (0 or 1), Domain, Word, Frequency__.
+Evaluation metric is F2-score.
+
+
+Directory structure
+-------------------
+
+* `README.md` — this file
+* `config.txt` — configuration file
+* `train/` — directory with training data
+* `train/train.tsv` — train set
+* `dev-0/` — directory with dev (test) data
+* `dev-0/in.tsv` — input data for the dev set
+* `dev-0/expected.tsv` — expected (reference) data for the dev set
+* `test-A` — directory with test data
+* `test-A/in.tsv` — input data for the test set
+* `test-A/expected.tsv` — expected (reference) data for the test set

config.txt

@@ -0,0 +1 @@
+--metric F2 --precision 4

solution2.py

@@ -0,0 +1,136 @@
+import torch
+import pandas
+import re
+import numpy as np
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import precision_score, recall_score, accuracy_score
+
+learning_rate = torch.tensor(0.00001, dtype=torch.float)
+def f1_score(y_true, y_pred):
+    precision = precision_score(y_true, y_pred, average='micro')
+    recall = recall_score(y_true, y_pred, average='micro')
+    F1 = 2 * (precision * recall) / (precision + recall)
+    return F1
+
+W = torch.rand([4,16],dtype=torch.float, requires_grad=True)
+b = torch.rand(16,dtype=torch.float, requires_grad=True)
+U = torch.rand(16,dtype=torch.float, requires_grad=True)
+c = torch.rand(1,dtype=torch.float, requires_grad=True)
+
+
+def count_polish_diacritics(x):
+    x_counts = []
+    for i, word in x.iteritems():
+        c = len(re.findall(r'[ąćęłńóśźż]', str(word)))
+        x_counts.append(c)
+    return x_counts
+
+
+def Normalize(data, d = None):
+    if (d is None):
+        d = data
+    r = data - d.min()
+    return r/(d.max() - d.min())
+
+train_data = pandas.read_csv('train/train.tsv', sep='\t', names=['Sane', 'Domain', 'Word', 'Frequency'], header=None)
+x1 = Normalize(torch.tensor(train_data['Frequency'], dtype=torch.float))
+x2 = Normalize(torch.tensor(train_data['Word'].str.len(), dtype=torch.float))
+le = LabelEncoder()
+le.fit(train_data['Domain'])
+encoded_domain_col= le.transform(train_data['Domain'])
+x3 = torch.tensor(encoded_domain_col, dtype=torch.float)
+x4 = Normalize(torch.tensor(count_polish_diacritics(train_data['Word']),dtype=torch.float))
+x = torch.stack((x1,x2,x3,x4),0)
+y = torch.tensor(train_data['Sane'], dtype=torch.float)
+
+#dev data:
+dev_data = pandas.read_csv('dev-0/in.tsv', sep='\t', names=['Domain', 'Word', 'Frequency'], header=None)
+dev_x1 = Normalize(torch.tensor(dev_data['Frequency'], dtype=torch.float), x1)
+dev_x2 = Normalize(torch.tensor(dev_data['Word'].str.len(), dtype=torch.float), x2)
+
+dev_encoded_domain_col = le.transform(dev_data['Domain'])
+dev_x3 = torch.tensor(dev_encoded_domain_col, dtype=torch.float)
+dev_x4 = Normalize(torch.tensor(count_polish_diacritics(dev_data['Word']), dtype=torch.float), x4)
+dev_x = torch.stack((dev_x1, dev_x2, dev_x3, dev_x4), 0)
+dev_y_test = pandas.DataFrame(pandas.read_csv('dev-0/expected.tsv', encoding="utf-8", delimiter='\t', header=None))
+
+print("Training...")
+
+for _ in range(500):
+    W.requires_grad_(True)
+    b.requires_grad_(True)
+    c.requires_grad_(True)
+    U.requires_grad_(True)
+    for _ in range(1000):
+        h = torch.sigmoid(x.transpose(1, 0) @ W + b)
+        y_predicted = torch.sigmoid(h @ U + c)
+        cost = torch.sum((y_predicted - y) ** 2)
+        cost.backward()
+        with torch.no_grad():
+            W = W - learning_rate * W.grad
+            b = b - learning_rate * b.grad
+            c = c - learning_rate * c.grad
+            U = U - learning_rate * U.grad
+            W.requires_grad_(True)
+            b.requires_grad_(True)
+            c.requires_grad_(True)
+            U.requires_grad_(True)
+    W.requires_grad_(False)
+    b.requires_grad_(False)
+    c.requires_grad_(False)
+    U.requires_grad_(False)
+    print("Dev0 pred...")
+    # dev
+    dev_h = torch.sigmoid(dev_x.transpose(1, 0) @ W + b)
+    dev_y = torch.sigmoid(dev_h @ U + c)
+    dev_y = dev_y.numpy()
+    dev_y_pred = np.where(dev_y > 0.5, 1, 0)
+    score = f1_score(dev_y_test, dev_y_pred)
+    print("f1_score_dev0 within training: ", score, "\nAcc: ", accuracy_score(dev_y_test, dev_y_pred))
+
+W.requires_grad_(False)
+b.requires_grad_(False)
+c.requires_grad_(False)
+U.requires_grad_(False)
+
+print("Dev0 pred...")
+#dev
+
+
+dev_h = torch.sigmoid(dev_x.transpose(1, 0) @ W + b)
+dev_y = torch.sigmoid(dev_h @ U + c)
+dev_y = dev_y.numpy()
+dev_y_pred = np.where(dev_y > 0.5, 1, 0)
+#np.savetxt(f'./dev-0/out_float.tsv', dev_y, '%.f')
+with open('dev-0/out.tsv', 'w') as output_file:
+    for out in dev_y_pred:
+        print('%s' % out, file=output_file)
+with open('dev-0/out_float.tsv', 'w') as output_file:
+    for out in dev_y:
+        print('%s' % out, file=output_file)
+y_test = pandas.DataFrame(pandas.read_csv('dev-0/expected.tsv', encoding="utf-8", delimiter='\t', header=None))
+score = f1_score(y_test, dev_y_pred)
+print("f1_score_dev0 after training: ", score,"\nAcc: ", accuracy_score(dev_y_test, dev_y_pred))
+
+print("TestA pred...")
+#test-A
+testA_data = pandas.read_csv('dev-0/in.tsv', sep='\t', names=['Domain', 'Word', 'Frequency'], header=None)
+testA_x1 = Normalize(torch.tensor(testA_data['Frequency'], dtype=torch.float), x1)
+testA_x2 = Normalize(torch.tensor(testA_data['Word'].str.len(), dtype=torch.float), x2)
+
+testA_encoded_domain_col= le.transform(testA_data['Domain'])
+testA_x3 = torch.tensor(testA_encoded_domain_col, dtype=torch.float)
+testA_x4 = Normalize(torch.tensor(count_polish_diacritics(testA_data['Word']),dtype=torch.float), x4)
+testA_x = torch.stack((testA_x1,testA_x2,testA_x3,testA_x4),0)
+
+testA_h = torch.sigmoid(testA_x.transpose(1, 0) @ W + b)
+testA_y = torch.sigmoid(testA_h @ U + c)
+testA_y = testA_y.numpy()
+testA_y_pred = np.where(testA_y > 0.5, 1, 0)
+np.savetxt(f'./test-A/out_float.tsv', testA_y)
+with open('test-A/out.tsv', 'w') as output_file:
+    for out in testA_y_pred:
+        print('%s' % out, file=output_file)
+with open('test-A/out_float.tsv', 'w') as output_file:
+    for out in testA_y:
+        print('%s' % out, file=output_file)