#!/usr/bin/env python
# coding: utf-8

# # Simple Sentiment Analysis
# 
# This notebook shows how to analyze a collection of passages like Tweets for sentiment.
# 
# This is based on Neal Caron's [An introduction to text analysis with Python, Part 1](http://nealcaren.web.unc.edu/an-introduction-to-text-analysis-with-python-part-1/).
# 
# This Notebook shows how to analyze one tweet.

# ### Setting up our data
# 
# Here we will define the data to test our positive and negative dictionaries.

# In[6]:


theTweet = "No food is good food. Ha. I'm on a diet and the food is awful and lame."
positive_words=['awesome','good','nice','super','fun','delightful']
negative_words=['awful','lame','horrible','bad']


# In[7]:


type(positive_words)


# ### Tokenizing the text
# 
# Now we will tokenize the text.

# In[8]:


import re
theTokens = re.findall(r'\b\w[\w-]*\b', theTweet.lower())
print(theTokens[:10])


# ### Calculating postive words
# 
# Now we will count the number of positive words.

# In[14]:


numPosWords = 0
for banana in theTokens:
    if banana in positive_words:
        numPosWords += 1
print(numPosWords) 


# ### Calculating negative words
# 
# Now we will count the number of negative words.

# In[10]:


numNegWords = 0
for word in theTokens:
    if word in negative_words:
        numNegWords += 1
print(numNegWords) 


# In[18]:


v1 = "0"
v2 = 0
v3 = str(v2)
v1 == v3


# ### Calculating percentages
# 
# Now we calculate the percentages of postive and negative.

# In[11]:


numWords = len(theTokens)
percntPos = numPosWords / numWords
percntNeg = numNegWords / numWords
print("Positive: " + "{:.0%}".format(percntPos) + "  Negative: " + "{:.0%}".format(percntNeg))


# ### Deciding if it is postive or negative
# 
# We are going assume that a simple majority will define if the Tweet is positive or negative.

# In[12]:


if numPosWords > numNegWords:
    print("Positive " + str(numPosWords) + ":" + str(numNegWords))
elif numNegWords > numPosWords:
    print("Negative " + str(numPosWords) + ":" + str(numNegWords))
elif numNegWords == numPosWords:
    print("Neither " + str(numPosWords) + ":" + str(numNegWords))
    
print()


# 

# ## Next Steps

# Let's try another utility example, this time looking at more [Complex Sentiment Analysis](ComplexSentimentAnalysis.ipynb).

# ---
# [CC BY-SA](https://creativecommons.org/licenses/by-sa/4.0/) From [The Art of Literary Text Analysis](../ArtOfLiteraryTextAnalysis.ipynb) by [Stéfan Sinclair](http://stefansinclair.name) &amp; [Geoffrey Rockwell](http://geoffreyrockwell.com). Edited and revised by [Melissa Mony](http://melissamony.com). <br >Created August 8, 2014  (Jupyter 4.2.1)

# In[ ]: