Create keras1.py

keras1.py

@@ -0,0 +1,36 @@
+
+import pandas as pd
+import numpy as np
+import pickle
+from keras.preprocessing.text import Tokenizer
+from keras.models import Sequential
+from keras.layers import Activation, Dense, Dropout
+#from sklearn.preprocessing import LabelBinarizer
+#import sklearn.datasets as skds
+from pathlib import Path
+
+
+
+# For reproducibility
+np.random.seed(1237)
+
+# Source file directory
+path_train = "U:\\data\\wos_bib_random_nastates.csv"
+
+files_train = skds.load_files(path_train,load_content=False)
+
+label_index = files_train.target
+label_names = files_train.target_names
+labelled_files = files_train.filenames
+
+data_tags = ["filename","category","news"]
+data_list = []
+
+# Read and add data from file to a list
+i=0
+for f in labelled_files:
+    data_list.append((f,label_names[label_index[i]],Path(f).read_text()))
+    i += 1
+
+# We have training data available as dictionary filename, category, data
+data = pd.DataFrame.from_records(data_list, columns=data_tags)