linear regression

.idea/.gitignore

@@ -0,0 +1,2 @@
+# Default ignored files
+/workspace.xml

.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 (paranormal-or-skeptic-ISI-public-bayes-2)" 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/retroc2-linear-regression.iml" filepath="$PROJECT_DIR$/.idea/retroc2-linear-regression.iml" />
+    </modules>
+  </component>
+</project>

.idea/retroc2-linear-regression.iml

@@ -0,0 +1,8 @@
+<?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 (paranormal-or-skeptic-ISI-public-bayes-2)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

.ipynb_checkpoints/logistic regression-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

main.py

@@ -0,0 +1,37 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LinearRegression
+
+df = pd.read_csv('./train/train.tsv', header=None, sep='\t')
+df['mean'] = (df.iloc[:, 0] + df.iloc[:, 1]) / 2
+
+vect = TfidfVectorizer()
+x_train_vect = vect.fit_transform(df[4])
+
+# wytrenowany model jest zapisany jako "finalized_model.sav"
+reg = LinearRegression().fit(x_train_vect, df['mean'])
+
+
+# zapis modelu
+# import pickle
+# filename = 'finalized_model.sav'
+# pickle.dump(reg, open(filename, 'wb'))
+
+
+# predykcje dla dev-1
+x_test = pd.read_csv('./dev-1/in.tsv', header=None, sep='\t')
+y_test = pd.read_csv('./dev-1/expected.tsv', header=None, sep='\t')
+
+x_test_vect = vect.transform(x_test[0])
+y_pred = reg.predict(x_test_vect)
+
+pd.DataFrame(y_pred).to_csv('./dev-1/out.tsv', header=None, sep='\t', index=False)
+
+# predykcje dla dev-0
+x_test_dev0 = pd.read_csv('./dev-0/in.tsv', header=None, sep='\t')
+y_test_dev0 = pd.read_csv('./dev-0/expected.tsv', header=None, sep='\t')
+
+x_test_dev0_vect = vect.transform(x_test_dev0[0])
+y_pred_dev_0 = reg.predict(x_test_dev0_vect)
+
+pd.DataFrame(y_pred_dev_0).to_csv('./dev-0/out.tsv', header=None, sep='\t', index=False)