going to pytorch on conda eve

.idea/misc.xml

@@ -3,5 +3,5 @@
   <component name="JavaScriptSettings">
     <option name="languageLevel" value="ES6" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (AL-2020)" project-jdk-type="Python SDK" />
 </project>

.idea/workspace.xml

@@ -20,9 +20,10 @@
   </component>
   <component name="ChangeListManager">
     <list default="true" id="828778c9-9d97-422f-a727-18ddbd059b85" name="Default Changelist" comment="po">
-      <change afterPath="$PROJECT_DIR$/coder/dataset/test.csv" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/coder/dataset/train.csv" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/coder/digits_recognizer.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/.idea/misc.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/misc.xml" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/.idea/wozek.iml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/wozek.iml" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/coder/image.py" beforeDir="false" afterPath="$PROJECT_DIR$/coder/image.py" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
@@ -82,7 +83,7 @@
       <recent name="C:\Users\Pawel Lukaszewicz\PycharmProjects\AL-2020\coder" />
     </key>
   </component>
-  <component name="RunManager" selected="Python.image">
+  <component name="RunManager" selected="Python.digits_recognizer">
     <configuration default="true" type="PythonConfigurationType" factoryName="Python">
       <module name="wozek" />
       <option name="INTERPRETER_OPTIONS" value="" />
@@ -105,22 +106,19 @@
       <option name="INPUT_FILE" value="" />
       <method v="2" />
     </configuration>
-    <configuration name="feature_hashing" type="PythonConfigurationType" factoryName="Python" temporary="true">
+    <configuration name="digits_recognizer" type="PythonConfigurationType" factoryName="Python" temporary="true" nameIsGenerated="true">
       <module name="wozek" />
       <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="$PROJECT_DIR$/Assiging" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$/coder" />
       <option name="IS_MODULE_SDK" value="true" />
       <option name="ADD_CONTENT_ROOTS" value="true" />
       <option name="ADD_SOURCE_ROOTS" value="true" />
       <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
-      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/Assiging/feature_hashing.py" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/coder/digits_recognizer.py" />
       <option name="PARAMETERS" value="" />
-      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="SHOW_COMMAND_LINE" value="true" />
       <option name="EMULATE_TERMINAL" value="false" />
       <option name="MODULE_MODE" value="false" />
       <option name="REDIRECT_INPUT" value="false" />
@@ -131,6 +129,9 @@
       <module name="wozek" />
       <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="$PROJECT_DIR$/coder" />
       <option name="IS_MODULE_SDK" value="true" />
@@ -215,17 +216,17 @@
     <list>
       <item itemvalue="Python.image" />
       <item itemvalue="Python.main" />
-      <item itemvalue="Python.feature_hashing" />
       <item itemvalue="Python.train_nn" />
       <item itemvalue="Python.rocognizer" />
+      <item itemvalue="Python.digits_recognizer" />
     </list>
     <recent_temporary>
       <list>
+        <item itemvalue="Python.digits_recognizer" />
         <item itemvalue="Python.image" />
         <item itemvalue="Python.rocognizer" />
         <item itemvalue="Python.train_nn" />
         <item itemvalue="Python.main" />
-        <item itemvalue="Python.feature_hashing" />
       </list>
     </recent_temporary>
   </component>
@@ -257,6 +258,11 @@
       <workItem from="1590230578314" duration="1895000" />
       <workItem from="1590235510565" duration="925000" />
       <workItem from="1590340739871" duration="8052000" />
+      <workItem from="1590359007619" duration="127000" />
+      <workItem from="1590409526059" duration="4922000" />
+      <workItem from="1590423569728" duration="2532000" />
+      <workItem from="1590436739719" duration="6325000" />
+      <workItem from="1590443664804" duration="2683000" />
     </task>
     <task id="LOCAL-00001" summary="create Shelf">
       <created>1589815443652</created>
@@ -328,7 +334,14 @@
       <option name="project" value="LOCAL" />
       <updated>1589972251988</updated>
     </task>
-    <option name="localTasksCounter" value="11" />
+    <task id="LOCAL-00011" summary="new dataset">
+      <created>1590359074952</created>
+      <option name="number" value="00011" />
+      <option name="presentableId" value="LOCAL-00011" />
+      <option name="project" value="LOCAL" />
+      <updated>1590359074952</updated>
+    </task>
+    <option name="localTasksCounter" value="12" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">
@@ -358,7 +371,8 @@
     <MESSAGE value="zwiekszenie dokladnosci" />
     <MESSAGE value="finding barcode" />
     <MESSAGE value="po" />
-    <option name="LAST_COMMIT_MESSAGE" value="po" />
+    <MESSAGE value="new dataset" />
+    <option name="LAST_COMMIT_MESSAGE" value="new dataset" />
   </component>
   <component name="WindowStateProjectService">
     <state x="115" y="162" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog" timestamp="1589923610328">
@@ -381,14 +395,14 @@
       <screen x="0" y="0" width="1536" height="824" />
     </state>
     <state width="1493" height="208" key="GridCell.Tab.0.right/0.0.1536.824@0.0.1536.824" timestamp="1589845242796" />
-    <state x="277" y="57" key="SettingsEditor" timestamp="1589845139218">
+    <state x="277" y="57" key="SettingsEditor" timestamp="1590443566792">
       <screen x="0" y="0" width="1536" height="824" />
     </state>
-    <state x="277" y="57" key="SettingsEditor/0.0.1536.824@0.0.1536.824" timestamp="1589845139218" />
-    <state x="361" y="145" key="Vcs.Push.Dialog.v2" timestamp="1589972275899">
+    <state x="277" y="57" key="SettingsEditor/0.0.1536.824@0.0.1536.824" timestamp="1590443566792" />
+    <state x="361" y="145" key="Vcs.Push.Dialog.v2" timestamp="1590359093497">
       <screen x="0" y="0" width="1536" height="824" />
     </state>
-    <state x="361" y="145" key="Vcs.Push.Dialog.v2/0.0.1536.824@0.0.1536.824" timestamp="1589972275899" />
+    <state x="361" y="145" key="Vcs.Push.Dialog.v2/0.0.1536.824@0.0.1536.824" timestamp="1590359093496" />
     <state x="54" y="145" width="672" height="678" key="search.everywhere.popup" timestamp="1589918982407">
       <screen x="0" y="0" width="1536" height="824" />
     </state>

.idea/wozek.iml

@@ -4,7 +4,7 @@
     <content url="file://$MODULE_DIR$">
       <excludeFolder url="file://$MODULE_DIR$/venv" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.8" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.8 (AL-2020)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyDocumentationSettings">

coder/digits_recognizer.py

@@ -0,0 +1,39 @@
+import numpy as np
+import torch
+import torchvision
+import matplotlib.pyplot as plt
+from time import time
+from torchvision import datasets, transforms
+from torch import nn, optim
+
+transform = transforms.Compose([transforms.ToTensor(),
+                                transforms.Normalize((0.5,), (0.5,)),
+                                ])
+
+trainset = datasets.MNIST('PATH_TO_STORE_TRAINSET', download=True, train=True, transform=transform)
+valset = datasets.MNIST('PATH_TO_STORE_TESTSET', download=True, train=False, transform=transform)
+trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
+valloader = torch.utils.data.DataLoader(valset, batch_size=64, shuffle=True)
+
+dataiter = iter(trainloader)
+images, labels = dataiter.next()
+
+print(images.shape)
+print(labels.shape)
+
+plt.imshow(images[0].numpy().squeeze(), cmap='gray_r')
+plt.show()
+
+# building nn model
+input_size = 784
+hidden_sizes = [128, 64]
+output_size = 10
+
+model = nn.Sequential(nn.Linear(input_size, hidden_sizes[0]),
+                      nn.ReLU(),
+                      nn.Linear(hidden_sizes[0], hidden_sizes[1]),
+                      nn.ReLU(),
+                      nn.Linear(hidden_sizes[1], output_size),
+                      nn.LogSoftmax(dim=1))
+print(model)
+

coder/image.py

@@ -7,11 +7,12 @@ from sklearn.neural_network import MLPClassifier
 import pandas as pd
 import cv2
 
-#28x28
-train_data = np.genfromtxt('dataset/train.csv', delimiter=',', skip_header=1 ,max_rows=20000, encoding='utf-8')
-test_data = np.genfromtxt('dataset/test.csv', delimiter=',' , skip_header=1, max_rows=20000, encoding='utf-8')
-
+# 28x28
+train_data = np.genfromtxt('dataset/train.csv', delimiter=',', skip_header=1, max_rows=20000, encoding='utf-8')
+test_data = np.genfromtxt('dataset/test.csv', delimiter=',', skip_header=1, max_rows=20000, encoding='utf-8')
 
+# train_data = pd.read_csv('dataset/train.csv')
+# test_data = pd.read_csv('dataset/test.csv')
 
 # training
 # recznie napisane cyfry
@@ -20,45 +21,46 @@ digits = datasets.load_digits()
 y = digits.target
 x = digits.images.reshape((len(digits.images), -1))
 
+# print(type(y[0]), type(x[0]))
+# ogarnac zbior, zwiekszyc warstwy
 
-#ogarnac zbior, zwiekszyc warstwy
+# x_train = train_data.iloc[:, 1:].values.astype('float32')
+# y_train = train_data.iloc[:, 0].values.astype('int32')
+# x_test = test_data.values.astype('float32')
 
-x_train = train_data[0:20000, 1:]
-y_train = train_data[0:20000, 0]
-x_test = test_data[0:20000]
-y_test = test_data[0:20000, 0]
+x_train = train_data[0:10000, 1:]
+y_train = train_data[0:10000, 0]
+x_test = train_data[10001:20000, 1:]
+y_test = train_data[10001:20000, 0].astype('int')
+
+print(type(y_test[0]), type(x_test[0]))
 
 # x_train = x[:900]
 # y_train = y[:900]
 # x_test = x[900:]
 # y_test = y[900:]
 
-print(x_test[0].shape, y_test[9].shape)
-
-mlp = MLPClassifier(hidden_layer_sizes=(100, 100, 100, 100), activation='logistic', alpha=1e-4,
+# 500, 500, 500, 500, 500
+mlp = MLPClassifier(hidden_layer_sizes=(150, 100, 100, 100), activation='logistic', alpha=1e-4,
                     solver='sgd', tol=0.000000000001, random_state=1,
-                    learning_rate_init=.1, verbose=True, max_iter=1000)
+                    learning_rate_init=.1, verbose=True, max_iter=10000)
 
 mlp.fit(x_train, y_train)
-print(123456789)
 predictions = mlp.predict(x_test)
-print(123456789)
 
 print("Accuracy: ", accuracy_score(y_test, predictions))
 
-
 # image
 
 img = cv2.cvtColor(cv2.imread('test5.jpg'), cv2.COLOR_BGR2GRAY)
-img = cv2.blur(img, (9, 9)) # poprawia jakosc
+img = cv2.blur(img, (9, 9))  # poprawia jakosc
 img = cv2.resize(img, (28, 28), interpolation=cv2.INTER_AREA)
 img = img.reshape((len(img), -1))
 
-print(type(img))
-print(img.shape)
-print(img)
-plt.imshow(img ,cmap='binary')
-plt.show()
+# print(type(img))
+# print(img.shape)
+# plt.imshow(img ,cmap='binary')
+# plt.show()
 
 data = []
 
@@ -67,15 +69,16 @@ for i in range(rows):
     for j in range(cols):
         k = img[i, j]
         if k > 225:
-            k = 0 # brak czarnego
+            k = 0  # brak czarnego
         else:
-            k = 1
+            k = 255
 
         data.append(k)
 
-data = np.asarray(data, dtype=np.float32)
-print(data)
+data = np.asarray(data, dtype=np.float64)
+# print(data)
+print(type(data))
 
 predictions = mlp.predict([data])
 
-print("Liczba to:", predictions[0])
+print("Liczba to:", predictions[0].astype('int'))