Merge pull request #30 from THIYAGU22/patch-3

text_preprocessing.py

ML Cookbook/text_preprocessing

@@ -0,0 +1,41 @@
+import shutil 
+
+from shutil import copyfile
+
+copyfile(src = "../input/cleantext/cleantext.py", dst = "../working/cleantext.py")
+
+# import all our functions
+from cleantext import *
+
+#!pylint cleantext
+
+import pandas as pd
+from sklearn.feature_extraction.text import CountVectorizer
+
+training = [
+    " I am master of all",
+    "I am a absolute learner"
+]
+
+generalization = [
+    "I am absolute learner learner"
+]
+
+vectorization = CountVectorizer(
+    stop_words = "english",
+    preprocessor = process.master_clean_text)
+
+vectorization.fit(training)
+
+build_vocab = {
+     value:key 
+     for key , value in vectorization.vocabulary_.items()
+}
+
+vocab = [build_vocab[i] for i in range(len(build_vocab))]
+
+pd.DataFrame(
+data = vectorization.transform(generalization).toarray(),
+    index=["generalization"],
+    columns=vocab
+)

text_preprocessing.py

@@ -0,0 +1,39 @@
+import clean_text
+
+# import all our functions
+from clean_text import *
+
+#!pylint cleantext
+
+import pandas as pd
+from sklearn.feature_extraction.text import CountVectorizer
+
+training = [
+    " I am master of all",
+    "I am a absolute learner"
+]
+
+generalization = [
+    "I am absolute learner learner"
+]
+
+vectorization = CountVectorizer(
+    stop_words = "english",
+    preprocessor = process.master_clean_text)
+
+vectorization.fit(training)
+
+build_vocab = {
+     value:key 
+     for key , value in vectorization.vocabulary_.items()
+}
+
+vocab = [build_vocab[i] for i in range(len(build_vocab))]
+
+extracted = pd.DataFrame(
+data = vectorization.transform(generalization).toarray(),
+    index=["generalization"],
+    columns=vocab
+)
+
+print(extracted)