diff --git a/A_Midsummer_Nights_Dream.pickle b/A_Midsummer_Nights_Dream.pickle
new file mode 100644
index 0000000..813f6c1
Binary files /dev/null and b/A_Midsummer_Nights_Dream.pickle differ
diff --git a/Alls_Well_That_Ends_Well.pickle b/Alls_Well_That_Ends_Well.pickle
new file mode 100644
index 0000000..abd192b
Binary files /dev/null and b/Alls_Well_That_Ends_Well.pickle differ
diff --git a/Antony_and_Cleopatra.pickle b/Antony_and_Cleopatra.pickle
new file mode 100644
index 0000000..927d07c
Binary files /dev/null and b/Antony_and_Cleopatra.pickle differ
diff --git a/Comedy_Of_Errors.pickle b/Comedy_Of_Errors.pickle
new file mode 100644
index 0000000..7ec037f
Binary files /dev/null and b/Comedy_Of_Errors.pickle differ
diff --git a/Coriolanus.pickle b/Coriolanus.pickle
new file mode 100644
index 0000000..ed36be7
Binary files /dev/null and b/Coriolanus.pickle differ
diff --git a/Cymbeline.pickle b/Cymbeline.pickle
new file mode 100644
index 0000000..e10877f
Binary files /dev/null and b/Cymbeline.pickle differ
diff --git a/Hamlet.pickle b/Hamlet.pickle
new file mode 100644
index 0000000..b5780ae
Binary files /dev/null and b/Hamlet.pickle differ
diff --git a/Julius_Caesar.pickle b/Julius_Caesar.pickle
new file mode 100644
index 0000000..df3b547
Binary files /dev/null and b/Julius_Caesar.pickle differ
diff --git a/King_Henry_IV.pickle b/King_Henry_IV.pickle
new file mode 100644
index 0000000..7486ee3
Binary files /dev/null and b/King_Henry_IV.pickle differ
diff --git a/King_John.pickle b/King_John.pickle
new file mode 100644
index 0000000..798f9ab
Binary files /dev/null and b/King_John.pickle differ
diff --git a/King_Richard_II.pickle b/King_Richard_II.pickle
new file mode 100644
index 0000000..cd392a9
Binary files /dev/null and b/King_Richard_II.pickle differ
diff --git a/Loves_Labours_Lost.pickle b/Loves_Labours_Lost.pickle
new file mode 100644
index 0000000..0f53237
Binary files /dev/null and b/Loves_Labours_Lost.pickle differ
diff --git a/Measure_for_Measure.pickle b/Measure_for_Measure.pickle
new file mode 100644
index 0000000..1c536d0
Binary files /dev/null and b/Measure_for_Measure.pickle differ
diff --git a/README.md b/README.md
index 8cce527..877b8c4 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,12 @@
-# TextMining
+To run this program you will need to download the GitHub repository as well as the Natural Language Toolkit (NKTL), the requests package and the Vader sentiment analysis package
 
-This is the base repo for the text mining and analysis project for Software Design at Olin College.
+The requests package is used to request date from the internet.  I can be downloaded by typing pip install requests into the windows command line.
+
+The Vader sentiment analysis package contains tools for preforming sentiment analysis. It can be downloaded by typing pip install vaderSentiment into the windows command line.
+
+The natural language toolkit has a wide variety of tools related to language. To download the NLTK simply type pip install nltk into your windows command line.
+
+After all of the appropriate packages are downloaded the go to the repository and type in python minebooks2.py into the command line.
+To run this program you will need to download the GitHub repository as well as the Natural Language Toolkit (NKTL), the requests package and the Vader sentiment analysis package
+
+The report for this project can be found at https://github.com/hthomas60/TextMining/blob/master/Report2.pdf
diff --git a/Report.pdf b/Report.pdf
new file mode 100644
index 0000000..8e68444
Binary files /dev/null and b/Report.pdf differ
diff --git a/Report2.pdf b/Report2.pdf
new file mode 100644
index 0000000..ac6ef58
Binary files /dev/null and b/Report2.pdf differ
diff --git a/_config.yml b/_config.yml
new file mode 100644
index 0000000..c50ff38
--- /dev/null
+++ b/_config.yml
@@ -0,0 +1 @@
+theme: jekyll-theme-merlot
\ No newline at end of file
diff --git a/loadBooks.py b/loadBooks.py
new file mode 100644
index 0000000..0deef1d
--- /dev/null
+++ b/loadBooks.py
@@ -0,0 +1,29 @@
+import pickle
+import requests
+import codecs
+
+def loadbooks():
+	"""
+	Loads books from gutenberg.org. Book id has to be manualy changed each book.
+	"""
+	downloaded_book = requests.get('http://www.gutenberg.org/ebooks/1522.txt.utf-8').text
+	return downloaded_book
+
+def savebook(book_text, filename):
+	"""
+	Saves a the text of a book into a file. 
+	"""
+	f = open(filename, 'wb')
+	pickle.dump(book_text, f)
+	f.close()
+
+def opensavedbook(file):
+	"""
+	Opens a file that is saved on the computer
+	"""
+	input_file = open(file, 'rb')
+	opened_text = pickle.load(input_file)
+	return opened_text
+
+
+
diff --git a/minebooks2.py b/minebooks2.py
new file mode 100644
index 0000000..cd9fff4
--- /dev/null
+++ b/minebooks2.py
@@ -0,0 +1,186 @@
+from loadBooks import *
+import string
+from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+import nltk
+from collections import defaultdict #frequwords
+import random
+import operator
+
+
+def removegutnburg(text):
+	"""
+	Removes the Gutenberg license information for so that the text can 
+	be analyzed.
+
+	"""
+	
+	licence = "ject Gutenberg Association / Carnegie Mellon University" #last line in license
+	bookstart = "by William Shakespeare" # set to Act V to
+	bookend = "THE END"
+	start_pos = text.find(licence) + 60 				#finds the end of the licensing agreement	
+	start_reading = text.find(bookstart,start_pos) + 22 #all of the books start with "title" by William Shakespeare
+	end_reading = text.find(bookend,start_reading ) 	#finds THE END at the end of the book
+	return (text[start_reading:end_reading])			#returns text of the play
+
+
+def loadjustbooks(playfiles):
+	"""
+	Takes a list of play names and a list of text files of those plays.
+	Removes Gutenberg license, newlines and punctuation from the play text.
+
+	Ex. Makes a list of all of the text of the comedic plays
+
+	"""
+
+	plays = []
+
+	
+	for i in playfiles:
+		play = opensavedbook(i)		#opens play text file
+		just_play = removegutnburg(play) #removes gutenberge license
+		just_play = RemoveAllButLettersAndSpaces(just_play) #removes newlines and punctuation
+		plays.append(just_play)		#adds current play to the play list
+
+	return plays #returns list of plays
+
+def RemoveAllButLettersAndSpaces(mystring):
+	"""
+	removes special characters and punctuation from play texts.
+	>>>  RemoveAllButLettersAndSpaces("\r\nqwetr.,")
+	'qwe2tr'
+	"""
+	toremove = ['\r', '\n','\'','[', ']','.','?', ';',':','-', '\"',',']
+	for c in toremove:
+		mystring = mystring.replace(c, ' ')
+
+	
+	return mystring.lower() #makes everything lower case words like "The" and "the" are the same
+
+def RunSentAnalysis(mylist):
+	"""
+	runs sentimient analysis and returns positive and negitive sentiments 
+	"""
+	res = []
+	analyzer = SentimentIntensityAnalyzer()
+	answer = analyzer.polarity_scores(mylist)
+	res.append(answer["pos"])
+	res.append(answer["neg"])
+	return res
+	
+
+def Most_Common(text):
+	"""
+	takes a string and returns the 25 most common words in the string
+	"""
+	top_words = []
+	freqwords = defaultdict(int) #initializes a dictionary
+	
+	for words in text.split(): #goes through a list of all the words in the string text
+		freqwords[words] += 1  #if a word is found add 1 to the counter
+	sortedwords = sorted(freqwords.items(), key=operator.itemgetter(1), reverse = True) #sorts dictionary of words based on how many times the word was found in reverse order. 
+	for i in range(25):
+		top_words.append(sortedwords[i][0])	#store the 25 most common words
+	return (top_words)						#Rreturns a list of the 24 most common words
+
+def commonOverAll(list1,list2,list3):
+	""" 
+	returns a list of all the most universally common words of all three story types
+
+	"""
+	
+	return( list(set(list(set(list1).intersection(list2))).intersection(list3)))
+
+def removewords(words,wordstoremove): 
+	"""
+	Removes words from the plays that are univeraly common amonge all types
+	"""
+	words = words.split()
+	return ([x for x in words if x not in wordstoremove]) #return elements in words that are not in wordstoremove
+
+def listtostring(mylist):
+	"""
+	convers a list of words to string of words
+	"""
+	return ' '.join(mylist)
+
+def linklists(mylist):
+	"""
+	Add several list together into one large list
+	"""
+	res = []
+	for i in range(len(mylist)):
+		res += [mylist[i]]
+	return listtostring(res)
+
+def sampling(mylist, trials):
+	pos = 0
+	neg = 0
+	for i in range(trials):
+		sample = listtostring(random.sample(mylist,10))
+		sentiment = RunSentAnalysis(sample)
+		pos += sentiment[0]
+		neg += sentiment[1]
+
+	return[pos/trials, neg/trials]
+
+
+def textmining(): # Main function that runs the textmining code.
+	"""
+	13 of Shakespeare’s plays were saved from gutenberg.org.
+	I sorted the file names of all of the plays into tree lists
+	comedies, tragedies, and histories.
+
+	"""
+	
+	comedies = ['A_Midsummer_Nights_Dream.pickle', 'Alls_Well_That_Ends_Well.pickle']
+	tragedies = ['Antony_and_Cleopatra.pickle','Coriolanus.pickle','Cymbeline.pickle']
+	histories = ['King_Henry_IV.pickle','King_John.pickle','King_Richard_II.pickle']
+
+
+	colletion = []								#list to store all three types of books
+	colletion.append(loadjustbooks(comedies))	#loads text from the comedies into the first element
+	colletion.append(loadjustbooks(tragedies))	#loads text from the trageties into the second element
+	colletion.append(loadjustbooks(histories))	#loads text from the histories into the second element
+														#collection was broken up into comedies, tragedies and
+														#histories to increase code readability
+	all_comedies = (linklists(colletion[0]))			#combines all of the saved comedies into one list
+	all_trageties = (linklists(colletion[1]))			#combines all of the saved trageties into one list
+	all_histories = (linklists(colletion[2]))			#combines all of the saved histories into one list
+
+	common_comedies = (Most_Common(all_comedies))		#finds the most common words in Shakespeare’s comedies
+	common_trageties = (Most_Common(all_trageties))		#finds the most common words in Shakespeare’s trageties
+	common_histories = (Most_Common(all_histories))		#finds the most common words in Shakespeare’s histories
+
+	common_words = (commonOverAll(common_comedies,common_trageties, common_histories)) #make a list of words common along all three play types
+
+	comedy_uncommon = removewords(all_comedies,common_words)		#removes the univeraly common words from the comedic plays
+	tragety_uncommon = removewords(all_trageties,common_words)	#removes the universally common words from the tragic plays
+	history_uncommon = removewords(all_histories,common_words)	#removes the universally common words from the historic plays
+
+	
+
+
+
+	print("\n")
+	print("Sentiment Analysis Average of Comedic Plays")
+	average = sampling(comedy_uncommon,500)		#preform Sentiment Analyses on all three play types
+	print (average)
+	print("Sentiment Analysis of Tragic Plays")
+	average = sampling(tragety_uncommon,500)		#preform Sentiment Analyses on all three play types
+	print (average)
+	print("Sentiment Analysis of Historic Plays")
+	average = sampling(tragety_uncommon,500)		#preform Sentiment Analyses on all three play types
+	print (average)
+	#RunSentAnalysis(tragic_string)
+	#print("\n")
+	#print("Sentiment Analysis of Historic Plays")
+	#RunSentAnalysis(historic_string)
+
+
+
+
+textmining()
+#if __name__ == "__main__":
+#    import doctest
+#doctest.testmod()
+