Your First Text Mining Project with Python in 3 steps

1. 1. Building a corpus — using Tweepy to gather sample text data from Twitter’s API.
   2. Analyzing text — analyzing the sentiment of a piece of text with our own SDK.
   3. Visualizing results — how to use Pandas and matplotlib to see the results of your work.

Step 1. Build a Corpus

pip install tweepy

>>> import tweepy

import tweepy, codecs

## fill in your Twitter credentials 
consumer_key = ‘your consumer key here’
consumer_secret = ‘your consumer secret key here’
access_token = ‘your access token here’
access_token_secret = ‘your access token secret here’

## let Tweepy set up an instance of the REST API
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)

## fill in your search query and store your results in a variable
results = api.search(q = "your search term here", lang = "en", result_type = "recent", count = 1000)

## use the codecs library to write the text of the Tweets to a .txt file
file = codecs.open("your text file name here.txt", "w", "utf-8")
for result in results:
	file.write(result.text)
	file.write("\n")
file.close()

Step 2. Analyze Sentiment

<span style="font-weight: 400;">pip install aylien-apiclient</span>

>>>from aylienapiclient import textapi

>>>from aylienapiclient import textapi
>>>client = textapi.Client("Your_app_ID", "Your_application_key")
>>>sentiment = client.Sentiment({'text': 'enter some of your own text here'})
>>>print(sentiment)

from aylienapiclient import textapi
import csv, io

## Initialize a new client of AYLIEN Text API
client = textapi.Client("your_app_ID", "your_app_key")

with io.open('Trump_Tweets.csv', 'w', encoding='utf8', newline='') as csvfile:
	csv_writer = csv.writer(csvfile)
	csv_writer.writerow(["Tweet", "Sentiment"])
	with io.open("Trump.txt", 'r', encoding='utf8') as f:
	    for tweet in f.readlines():
	    	## Remove extra spaces or newlines around the text
	    	tweet = tweet.strip()

	    	## Reject tweets which are empty so you don’t waste your API credits
	    	if len(tweet) == 0:
	    		print('skipped')
	    		continue
	    	
	    	print(tweet)

	    	## Make call to AYLIEN Text API
	    	sentiment = client.Sentiment({'text': tweet})

	    	## Write the sentiment result into csv file
	    	csv_writer.writerow([sentiment['text'], sentiment['polarity']])

Step 3. Visualize your Results

pip install matplotlib
pip install pandas

## import the libraries
import matplotlib.pyplot as plt 
import pandas as pd
from collections import Counter
import csv 

## open up your csv file with the sentiment results
with open('your_csv_file_from_step_2.csv', 'r', encoding = 'utf8') as csvfile:
	## use Pandas to read the “Sentiment” column,
        df = pd.read_csv(csvfile)
	sent = df["Sentiment"]

## use Counter to count how many times each sentiment appears
## and save each as a variable
	counter = Counter(sent)
	positive = counter['positive']
	negative = counter['negative']
	neutral = counter['neutral']

## declare the variables for the pie chart, using the Counter variables for “sizes”
labels = 'Positive', 'Negative', 'Neutral'
sizes = [positive, negative, neutral]
colors = ['green', 'red', 'grey']
yourtext = "Your Search Query from Step 2"

## use matplotlib to plot the chart
plt.pie(sizes, labels = labels, colors = colors, shadow = True, startangle = 90)
plt.title("Sentiment of 200 Tweets about "+yourtext)
plt.show()