restore point

Dokumentation/silas/w2vMean.tex

@@ -180,6 +180,7 @@ confusion_matrix(Y_test,y_pred,normalize='true')
 \end{lstlisting}
 \wip{Tabelle auswerten}
 \begin{table}[ht]
+    \def\arraystretch{1.3}
     \begin{center}
         \begin{tabular}{*{4}{R}}
             - &Negativ & Neutral & Positiv\\
@@ -195,6 +196,7 @@ von $85.7\%$, betrachtet man jedoch die Konfusionsmatrix in Tabelle \ref{tab:con
 sieht man das dort bloß $27\%$ der neutralen Rezensionen richtig klassifiziert wurden.
 \wip{Tabellenreferenz ???}
 \begin{table}[ht]
+    \def\arraystretch{1.3}
     \begin{center}
         \begin{tabular}{*{4}{R}}
             - &Negativ & Neutral & Positiv\\

Dokumentation/w2v.tex

@@ -74,7 +74,7 @@
 }
 
 \newcolumntype{R}{>{\collectcell\ApplyGradient}c<{\endcollectcell}}
-\renewcommand{\arraystretch}{1.5}
+%\renewcommand{\arraystretch}{1.5}
 \setlength{\fboxsep}{3mm} % box size
 \setlength{\tabcolsep}{5pt}
 %-----------------------

python/w2v_cnn_gen_hdf5.py

@@ -23,8 +23,8 @@ modelNN.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=
 #%%
 from hdf5 import hdf5Generator
 path = "G:\\ml\\"
-num_rows = 340000 
-batchSize = 512
+num_rows = 8000000 
+batchSize = 2048
 steps = num_rows/batchSize
 #early stop
 earlystop = keras.callbacks.EarlyStopping(monitor='accuracy',patience=10,verbose=False,restore_best_weights=True)

python/w2v_sentence_cnn.py

@@ -8,6 +8,7 @@ import pandas as pd
 import json
 
 from tensorflow.python.keras.constraints import MaxNorm
+from tensorflow.python.keras.layers.core import Dropout
 
 model_path = "D:\\ml\\full_yelp_w2v_model"
 #data_path ="C:\\Users\\sls21\\Documents\\Uni\\word2vec\\sample.json"
@@ -28,15 +29,15 @@ def getSentenceVectorCNN(sentence):
             i += 1
         except:
             pass
-    #if wordVecs == np.zeros((72,100)): #maybe dont alllow sentences with less than n wordvecotrs
-    #    raise Exception('words not found in w2v model')
+    if np.all(wordVecs[5:]==0):
+        raise Exception('not enough words found in w2v model')
     return wordVecs
 
 # %% data
 import numpy as np
 try:
-    X = np.load("./Data/X_cnn.npy")
-    Y = np.load("./Data/Y_cnn.npy")
+    X = np.load("D:/ml/data/X_cnn.npy")
+    Y = np.load("D:/ml/data/Y_cnn.npy")
 except:
     X = []
     Y = []
@@ -61,8 +62,8 @@ except:
         #Y.append(1 if y>2 else 0)
     X = np.array(X)
     Y = np.array(Y)
-    #np.save("./Data/X_cnn",X)
-    #np.save("./Data/Y_cnn",Y)
+    np.save("D:/ml/data/X_cnn.npy",X)
+    np.save("D:/ml/data/Y_cnn.npy",Y)
 # %% CNN 
 import tensorflow as tf
 import numpy as np
@@ -87,35 +88,29 @@ import tensorflow as tf
 import numpy as np
 from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import Dense, Flatten
-from tensorflow.keras.layers import Conv1D,MaxPooling1D,GlobalMaxPooling1D
+from tensorflow.keras.layers import Conv1D,MaxPooling1D,GlobalMaxPooling1D,Dropout
 from tensorflow import keras
 
 modelNN = Sequential()
 
 modelNN.add(Conv1D(32, 7, activation='relu',input_shape=(X[0].shape)))
 modelNN.add(Conv1D(32, 7, activation='relu'))
-#modelNN.add(GlobalMaxPooling1D())
+modelNN.add(GlobalMaxPooling1D())
 modelNN.add(Flatten())
 modelNN.add(Dense(512,activation='relu'))
+modelNN.add(Dropout(0.5))
 modelNN.add(Dense(128,activation='relu'))
-#modelNN.add(Dense(50,activation='relu',input_dim=X[0].size))
+modelNN.add(Dropout(0.25))
 modelNN.add(Dense(10,activation='relu'))
+modelNN.add(Dropout(0.1))
 modelNN.add(Dense(3,activation='softmax'))
 modelNN.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=["accuracy"])
 
 # %% fit
 #early stop
-earlystop = keras.callbacks.EarlyStopping(monitor='val_accuracy',patience=10,verbose=False,restore_best_weights=True)
+earlystop = keras.callbacks.EarlyStopping(monitor='val_accuracy',patience=5,verbose=False,restore_best_weights=True)
 cbList = [earlystop]
 
-hist = modelNN.fit(X,Y,epochs=1000,validation_split=0.2,batch_size=128,callbacks=cbList)
+hist = modelNN.fit(X,Y,epochs=50,validation_split=0.2,batch_size=128,callbacks=cbList)
 
 #%%
\ No newline at end of file
-## Notes
-# np.unique(Y,return_counts=True)
-# (array([0, 1]), array([ 77051, 272891], dtype=int64))
-# /Y.size
-# -> array([0.2201822, 0.7798178])
-# -> Unbalanced dataset
-
-#current val_acc ~ 91.5 %

python/w2v_sentence_cnn_gen.py

@@ -24,8 +24,8 @@ def getSentenceVectorCNN(sentence):
             i += 1
         except:
             pass
-    #if wordVecs == np.zeros((72,100)): #maybe dont alllow sentences with less than n wordvecotrs
-    #    raise Exception('words not found in w2v model')
+    if np.all(wordVecs[5:]==0):
+        raise Exception('not enough words found in w2v model')
     return wordVecs
 
 #%% Data Generator
@@ -85,7 +85,7 @@ modelNN.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=
 earlystop = keras.callbacks.EarlyStopping(monitor='val_accuracy',patience=25,verbose=False,restore_best_weights=True)
 cbList = [earlystop]
 num_rows = 350000 
-batchSize = 512
+batchSize = 2048
 
 #hist = modelNN.fit(generate_arrays_from_file('./sample.json',128),epochs=1000,validation_split=0.2,batch_size=128,callbacks=cbList)
 train = generate_arrays_from_file('D:\\ml\\data\\train.json',batchSize)