def main():
# prompts user for the files that they would like to analyze
tweetFile = input(
"Please enter the name of the tweet file you wish to process: ")
keyFile = input(
"Please enter the name of the keyword file you wish to use: ")
# takes the files and uses the function compute_tweets to return a list of values
values = compute_tweets(tweetFile, keyFile)
# takes the list of values and prints them in a readable fashion
print("\nEastern Region Results")
print("%-35s" % "Happiness score:", values[0][0],
"\n%-35s" % "Number of keyword tweets:", values[0][1],
"\n%-35s" % "Total number of tweets:", values[0][2])
print("\nCentral Region Results")
print("%-35s" % "Happiness score:", values[1][0],
"\n%-35s" % "Number of keyword tweets:", values[1][1],
"\n%-35s" % "Total number of tweets:", values[1][2])
print("\nMountain Region Results")
print("%-35s" % "Happiness score:", values[2][0],
"\n%-35s" % "Number of keyword tweets:", values[2][1],
"\n%-35s" % "Total number of tweets:", values[2][2])
print("\nPacific Region Results")
print("%-35s" % "Happiness score:", values[3][0],
"\n%-35s" % "Number of keyword tweets:", values[3][1],
"\n%-35s" % "Total number of tweets:", values[3][2])
def main():
tweet_file_name = str(input("Please submit the file with the tweets: ")
) # Get's the file with the tweets
keyword_file_name = str(input("Please submit the file with the keywords: ")
) # Get's the file with the keywords
files = file_extension(
tweet_file_name,
keyword_file_name) # Checks the extensions on the file names
sentiments = sentiment_analysis.compute_tweets(files[0], files[1])
print("Eastern tweet results: Average: " + str(sentiments[0][0]) +
", number of keyword tweets: " + str(sentiments[0][1]) +
", number of tweets in region: " +
str(sentiments[0][2])) # Prints the value compute tweets returns
print("Central tweet results: Average: " + str(sentiments[1][0]) +
", number of keyword tweets: " + str(sentiments[1][1]) +
", number of tweets in region: " +
str(sentiments[1][2])) # Prints the value compute tweets returns
print("Mountain tweet results: Average: " + str(sentiments[2][0]) +
", number of keyword tweets: " + str(sentiments[2][1]) +
", number of tweets in region: " +
str(sentiments[2][2])) # Prints the value compute tweets returns
print("Pacific tweet results: Average: " + str(sentiments[3][0]) +
", number of keyword tweets: " + str(sentiments[3][1]) +
", number of tweets in region: " +
str(sentiments[3][2])) # Prints the value compute tweets returns
def main():
tweetFile = input("Please enter the name of the file containing tweets: ")
keywordFile = input("Please enter the name of the file containing keywords: ")
timezoneHappinessList = compute_tweets(tweetFile, keywordFile)
if timezoneHappinessList == []:
print(timezoneHappinessList)
else:
eastern = timezoneHappinessList[0]
central = timezoneHappinessList[1]
mountain = timezoneHappinessList[2]
pacific = timezoneHappinessList[3]
print('Eastern timezone: average "happiness value" = %s, number of tweets = %d' % (str(eastern[0]), eastern[1]))
print('Central timezone: average "happiness value" = %s, number of tweets = %d' % (str(central[0]), central[1]))
print('Mountain timezone: average "happiness value" = %s, number of tweets = %d' % (str(mountain[0]), mountain[1]))
print('Pacific timezone: average "happiness value" = %s, number of tweets = %d' % (str(pacific[0]), pacific[1]))
return
def main():
# Introductory statement
print("Welcome to the Sentiment Calculator.")
print("")
# Prompt the user to input the name of the file of tweets and the file of keywords
tweets = input("Please enter the name of the file with the Tweets: ")
keywords = input("Please enter the name of the file with the Keywords: ")
# Send the two files to function "compute_tweets" and set the return list value as scoreData
scoreData = compute_tweets(tweets, keywords)
print("")
# Only perform actions in if-statement if scoreData is not an empty list
if len(scoreData) != 0:
# Print out the results in 4 sections based on time-zone
for i in range(0,4):
if i == 0:
print("EASTERN REGION")
elif i == 1:
print("CENTRAL REGION")
elif i == 2:
print("MOUNTAIN REGION")
else:
print("PACIFIC REGION")
# Print the associated average happiness score, number of keyword tweets and number of tweets
# of each time-zone. This is stored in scoreData.
print("")
print("Average Happiness Score: ",scoreData[i][0])
print("Number of Keyword Tweets: ",scoreData[i][1])
print("Number of Tweets: ",scoreData[i][2])
print("")
print("")
from sentiment_analysis import compute_tweets # Imports the function from the sentiment_analysis file
done = False # Defines done as false
while not done: # Loop runs as long as done is false
try:
print()
keywords = input(
"Please enter the name of the file containing keywords"
) # Prompts user for keyword file
tweets = input("Please enter the name of the file containing tweets"
) # Prompts user for tweets file
results = compute_tweets(
tweets,
keywords) # Calls the compute_tweets function to get results
print("** Sentiment analysis complete! **") # End statement is printed
print(results) # Results are printed
print()
done = True # Makes done become true and exits the while loop
# This segment handles various errors with the use of exceptions
except IOError:
print(
"TWEET COUNT ZERO: One or more files were not found. Empty list returned, please try again."
)
except ValueError:
print("TWEET COUNT ZERO: file contents invalid, please try again.")
except ZeroDivisionError:
from sentiment_analysis import compute_tweets
#Asking the user to input which files they would like to use
tweets = str(input("Which tweet list do you want?"))
keylist = str(input("Which keylist do you want?"))
#If the name they entered does not contain .txt then you would add it for them
if ".txt" not in tweets:
tweets = tweets + ".txt"
if ".txt" not in keylist:
keylist = keylist + ".txt"
#Creating the list of timezones and computing it for all of them
#Output each item in the list and what they are
mass_list = compute_tweets(tweets, keylist)
for n in range(len(mass_list)):
if n == 0:
print("Eastern time: ")
print("Happiness Score:", mass_list[n][0])
print("Number of keyword tweets", mass_list[n][1])
print("Number of tweets", mass_list[n][2])
if n == 1:
print("Central time: ")
print("Happiness Score:", mass_list[n][0])
print("Number of keyword tweets", mass_list[n][1])
print("Number of tweets", mass_list[n][2])
if n == 2:
print("Mountain time: ")
print("Happiness Score:", mass_list[n][0])
print("Number of keyword tweets", mass_list[n][1])
print("Number of tweets", mass_list[n][2])
if n == 3:
#
#
#
from sentiment_analysis import compute_tweets
# ask for user input to determine analysis
fileName = input("Enter the name of your file: ")
keyword_fileName = input("Enter the name of your keywords list file: ")
file_analysis = compute_tweets(fileName, keyword_fileName)
# printing readable version of data to 3 decimals for each region
print("\nEastern Data")
print("Average happiness: %.3f" % file_analysis[0][0])
print("Number of key tweets: ", file_analysis[0][1])
print("Number of Eastern tweets: ", file_analysis[0][2])
print()
print("Central Data")
print("Average happiness: %.3f " % file_analysis[1][0])
print("Number of key tweets: ", file_analysis[1][1])
print("Number of Eastern tweets: ", file_analysis[1][2])
print()
print("Mountain Data")
print("Average happiness: %.3f" % file_analysis[2][0])
print("Number of key tweets: ", file_analysis[2][1])
print("Number of Eastern tweets: ", file_analysis[2][2])
print()
print("Pacific Data")
##
# Name: Abdalla Abdelhady
# Student Number: 250856115
# This module defines a functions that takes two files, one with tweets and one with keywords and sentiment values,
#and calculates an average sentiment value for each timezone in continental United States
#
#This part imports the module with the function that calculates sentiment values
import sentiment_analysis
#This part asks the user for the names of the files
tfile = input("What is the name of the file with tweets? ")
kfile = input("What is the name of the file with keywords? ")
finalvalues = sentiment_analysis.compute_tweets(tfile, kfile)
#This part outputs the results from the function in a format the user can read
print(
"The (happiness_score, number_of_keyword_tweets, number_of_tweets) in the eastern, central, mountain and pacific regions respectively are as shown below:\n",
finalvalues)
# Nov 14 2018
# Filip Durca
# This program asks the user for the name of the files containing the tweets and the keywords, and then outputs the results from each timezone
#imports
import sentiment_analysis
#Variables
timezones = ["Eastern", "Central", "Mountain", "Pacific"]
#Ask the user for the file names
tweetFile = input("What file are the tweets located in? ")
keywordFile = input("What file are the keywords located in? ")
#Get the results
results = sentiment_analysis.compute_tweets(tweetFile, keywordFile)
#Print the results only if file is found
if len(results) > 0:
for i in range(4):
print("Timezone:", timezones[i])
print("Average:", results[i][0], " Number of tweets:", results[i][1])
"""
Name: Jessica Yang
Program: Assignment 3, Sentiment Analysis
Program Description: analyzes twitter data and sentiment values
"""
import sentiment_analysis as s
# prompts user for tweet and key word list
tweet = input("Which tweet? ")
keyword = input("Which keyword list? ")
# calculates the scores from the given tweet and keywords
master_list = s.compute_tweets(tweet, keyword)
# print statements for empty master list
if master_list == (0, 0, 0, 0):
for x in range(4):
if x == 0:
print("Eastern")
if x == 1:
print("Central")
if x == 2:
print("Mountain")
if x == 3:
print("Pacific")
for y in range(3):
if y == 0:
print("Happiness Score: ", "0")
if y == 1:
from sentiment_analysis import compute_tweets
tweets = input("Please enter the name of the tweets file")
poskey = input("Please enter the name of the positive keywords file")
negkey = input("Please enter the name of the negative keywords file")
results = compute_tweets(
tweets, poskey,
negkey) #calling the compute function to find the results for each region
print("Total positive tweets is ", results[0], "and total negative tweets is ",
results[1], "out of ", results[2], "total tweets")
print("The overall score is ", results[3])
from sentiment_analysis import compute_tweets
# My name is Connor Haines, and this is my sentiment analysis assignment.
# This software uses a combination of files and functions, to calculate the average
# sentiment per tweet in specific timezones. The program refers to files full of
# tweets and keywords which are inputted by the user.
finalList = []
# Getting user to input file names.
tfilename = input("Enter the name of a tweets file: ")
kfilename = input("Enter the name of a keywords file: ")
# Executing "compute_tweets" function.
finalList = compute_tweets(tfilename, kfilename)
# Finally outputting values in a readable fashion.
print("")
print("----------(Average Sentiment, Number of Tweets)----------")
print("")
if len(finalList) > 1:
print("Eastern Timezone: ", finalList[0])
print("Central Timezone: ", finalList[1])
print("Mountain Timezone: ", finalList[2])
print("Pacific Timezone: ", finalList[3])
# Checking if empty list was returned and outputting a message.
else:
print("Empty list returned. Invalid file name(s).")
from sentiment_analysis import compute_tweets
tweets = input("Please enter the name of the tweets file")
keywords = input("Please enter the name of the keywords file")
results = compute_tweets(
tweets, keywords
) #calling the compute function to find the results for each region
#printing out the results in a readable form
if results != []:
print("EASTERN:", "\nHappiness Score: ", results[0][0],
"\nNumber of Tweets in Timezone: ", results[0][1],
"\nTotal Number of Tweets in Timezone: ", results[0][2], "\n")
print("CENTRAL:", "\nHappiness Score: ", results[1][0],
"\nNumber of Tweets in Timezone: ", results[1][1],
"\nTotal Number of Tweets in Timezone: ", results[1][2], "\n")
print("MOUNTAIN:", "\nHappiness Score: ", results[2][0],
"\nNumber of Tweets in Timezone: ", results[2][1],
"\nTotal Number of Tweets in Timezone: ", results[2][2], "\n")
print("PACIFIC:", "\nHappiness Score: ", results[3][0],
"\nNumber of Tweets in Timezone: ", results[3][1],
"\nTotal Number of Tweets in Timezone: ", results[3][2])
else:
print("EASTERN:", "\nHappiness Score: 0",
"\nNumber of Tweets in Timezone: 0",
"\nTotal Number of Tweets in Timezone: 0", "\n")
print("CENTRAL:", "\nHappiness Score: 0",
"\nNumber of Tweets in Timezone: 0",
"\nTotal Number of Tweets in Timezone: 0", "\n")
print("MOUNTAIN:", "\nHappiness Score: 0",
"\nNumber of Tweets in Timezone: 0",
# imports
from sentiment_analysis import compute_tweets
# asking for user input
tweets = input("Please enter the file name for the tweets: ")
keywords = input("Please enter the file name for the keywords: ")
# setting variable and using compute_tweets function
tupleList = compute_tweets(tweets, keywords)
# checks to see if the output was a [], if so that means the keywords file did not exist
if tupleList != []:
# formatting output
print("\nEASTERN:\nAverage happiness score:", tupleList[0][0],
"\nTotal number of keyword tweets:", tupleList[0][1],
"\nTotal number of tweets is:", tupleList[0][2])
print("\nCENTRAL:\nAverage happiness score:", tupleList[1][0],
"\nTotal number of keyword tweets:", tupleList[1][1],
"\nTotal number of tweets is:", tupleList[1][2])
print("\nMOUNTAIN:\nAverage happiness score:", tupleList[2][0],
"\nTotal number of keyword tweets:", tupleList[2][1],
"\nTotal number of tweets is:", tupleList[2][2])
print("\nPACIFIC:\nAverage happiness score:", tupleList[3][0],
"\nTotal number of keyword tweets:", tupleList[3][1],
"\nTotal number of tweets is:", tupleList[3][2])
else:
print(tupleList)
from sentiment_analysis import compute_tweets
from sentiment_analysis import printer
fileName = input("Please enter a tweets file: ")
keyName = input("Please enter a key: ")
finalAnswer = compute_tweets(fileName, keyName)
finalAnswer = list(finalAnswer)
for i in range(0, len(finalAnswer)):
finalAnswer[i] = list(finalAnswer[i])
try:
Eastern = finalAnswer[0]
Eastern.append("Eastern")
Central = finalAnswer[1]
Central.append("Central")
Mountain = finalAnswer[2]
Mountain.append("Mountain")
Pacific = finalAnswer[3]
Pacific.append("Pacific")
print(" ")
print("SENTIMENT VALUE RESULTS:")
print(" ")
printer(Eastern)
printer(Central)
printer(Mountain)
printer(Pacific)
except IndexError:
print(finalAnswer)
from sentiment_analysis import compute_tweets #importing the necessary function from the sentiment_analysis module
userFile = input("Enter the name of the file with the tweets: ") #taking user input
userKey = input("Enter the name of the file with keywords: ")
output = compute_tweets(userFile, userKey) #using the compute_tweets function to output the results after file processing
def formatOutput(output): #this function outputs the values for the user
print("Happiness Value: ", round(output[0],3)) #rounding the happiness value in a region to 3 digits
print("Tweet with Keywords: ", output[1])
print("Total Number of Tweets: ", output[2])
if len(output) > 0: #prints the output if the list contains anything (so that if an exception is generated the empty list doesn't get formatted)
print("\nEASTERN: ")
formatOutput(output[0])
print("\nCENTRAL: ")
formatOutput(output[1])
print("\nMOUNTAIN: ")
formatOutput(output[2])
print("\nPACIFIC: ")
formatOutput(output[3])
else:
print(output)
from sentiment_analysis import compute_tweets
TWEET_FILE=input('Please enter the name of the tweet file: ')
KEYWORD_FILE=input('Please enter the name of the keyword file: ')
print('')
x=compute_tweets(TWEET_FILE,KEYWORD_FILE)
#try is used so if the wrong file is entered then it would simply ask to input a right file
try:
#int(x[0][1])
#this is used to compare the regions happiness score and find out which region is the happiest
if x[0][0]>x[1][0] and x[0][0]>x[2][0] and x[0][0]>x[3][0]:
print('The Eastern Time Zone is the happiest region')
elif x[1][0]>x[0][0] and x[1][0]>x[2][0] and x[1][0]>x[3][0]:
print('The Central Time Zone is the happiest region')
elif x[2][0]>x[0][0] and x[2][0]>x[1][0] and x[2][0]>x[3][0]:
print('The Mountain Time Zone is the happiest region')
elif x[3][0]>x[0][0] and x[3][0]>x[1][0] and x[3][0]>x[2][0]:
print('The Pacific Time Zone is the happiest region')
#print statments for the happiness value, keyword tweets & total number of tweets for all regions
print('')
print('The happiness value for the EASTERN TIME ZONE is : ', x[0][0])
print('The total number of key word tweets for the EASTERN TIME ZONE is: ',x[0][1])
print('The total number of tweets for EASTERN TIME ZONE is: ',x[0][2])
print('')
print('The happiness value for the CENTRAL TIME ZONE is : ',x[1][0])
print('The total number of key word tweets for the CENTRAL TIME ZONE is: ',x[1][1])
print('The total number of tweets for CENTRAL TIME ZONE is: ',x[1][2])
print('')
print('The happiness value for the MOUNTAIN TIME ZONE is : ',x[2][0])
#Assignment 3: Sentiment Analysis
#Andrea Lee 250836721
import sentiment_analysis
input_tweet = input(
'Enter tweet file name:\n') #prompt user for tweet file name
input_keyword = input(
'Enter keyword file name:\n') #prompt user for keyword file name
scores = sentiment_analysis.compute_tweets(
input_tweet, input_keyword
) #call compute_tweets function from sentiment_analysis module to get happiness scores and number of counted tweets for each region
#print output
print()
if len(scores) == 0: #blank list is returned if invalid file name
print('File name does not exist.'
) #if blank list is returned, print file name does not exist)
else:
eastern_score = scores[0]
eastern_happiness_score = eastern_score[0]
eastern_counted_tweet = eastern_score[1]
central_score = scores[1]
central_happiness_score = central_score[0]
central_counted_tweet = central_score[1]
# Name: Carrie Lu
# Date: November 18, 2020
# Description: This program performs a simple sentiment analysis on Twitter data and
# determines the happiness score, number of tweets, and total number of tweets in each timezone (Eastern, Central, Mountain, Pacific).
from sentiment_analysis import compute_tweets
# Prompt user to enter the name of the file containing the tweets and the file containing the keywords
user_file = input('Enter name of file with tweets:')
user_keywords_file = input('Enter file name of file with keywords:')
results = compute_tweets(user_file, user_keywords_file)
# Output the results in a readable form
if results != []:
print("EASTERN:", "\nHappiness Score: ", results[0][0], "\nNumber of Tweets in Timezone: ", results[0][1],
"\nTotal Number of Tweets in Timezone: ", results[0][2], "\n")
print("CENTRAL:", "\nHappiness Score: ", results[1][0], "\nNumber of Tweets in Timezone: ", results[1][1],
"\nTotal Number of Tweets in Timezone: ", results[1][2], "\n")
print("MOUNTAIN:", "\nHappiness Score: ", results[2][0], "\nNumber of Tweets in Timezone: ", results[2][1],
"\nTotal Number of Tweets in Timezone: ", results[2][2], "\n")
print("PACIFIC:", "\nHappiness Score: ", results[3][0], "\nNumber of Tweets in Timezone: ", results[3][1],
"\nTotal Number of Tweets in Timezone: ", results[3][2])
else:
print("EASTERN:", "\nHappiness Score: 0", "\nNumber of Tweets in Timezone: 0",
"\nTotal Number of Tweets in Timezone: 0", "\n")
print("CENTRAL:", "\nHappiness Score: 0", "\nNumber of Tweets in Timezone: 0",
"\nTotal Number of Tweets in Timezone: 0", "\n")
print("MOUNTAIN:", "\nHappiness Score: 0", "\nNumber of Tweets in Timezone: 0",
"\nTotal Number of Tweets in Timezone: 0", "\n")
print("PACIFIC:", "\nHappiness Score: 0", "\nNumber of Tweets in Timezone: 0",
"\nTotal Number of Tweets in Timezone: 0")
# import the tweeting computing function from the sentiment analysis module created
from sentiment_analysis import compute_tweets
# This will be used to loop the input requests
# If an invalid file name is entered
valid = True
print("Hello!")
# Request the keyword and tweet file
tweets = input("Please enter the name of the file containing the tweets:")
key = input("Please enter the name of the file containing the key words:")
print("Thank you! Now I will be able to process the tweets.\n")
# Use the function to process the tweets' average sentiment and counted tweet values by region
results = compute_tweets(tweets, key)
# Until an invalid file is entered
while valid:
# Split the tuples of the happiness average and counted tweets if they exist
try:
eastResult = str(results[0]).split(",")
centralResult = str(results[1]).split(",")
mountainResult = str(results[2]).split(",")
pacificResult = str(results[3]).split(",")
# Display calculated results
print("\nIn the Eastern region, the happiness average is,",
eastResult[0].replace("(", ""), "with",
eastResult[1].replace(")", ""), "counted tweets.")
from sentiment_analysis import compute_tweets #importing function
#if a user enters a correct file
validFile = False
while not validFile:
try:
#prompting the user to input desired files
tweets = input("Please enter a file containing tweets: ")
keywords = input("Please enter a file containing keywords: ")
output = (compute_tweets(tweets, keywords)) #calling the function
#printing the results for each region
print("\nFor the Eastern timezone, the average score of happiness is:",
output[0][0])
print("There were", output[0][1], "tweets counted. \n")
print("For the Central timezone, the average score of happiness is:",
output[1][0])
print("There were", output[1][1], "tweets counted. \n")
print("For the Mountain timezone, the average score of happiness is:",
output[2][0])
print("There were", output[2][1], "tweets counted. \n")
print("For the Pacific timezone, the average score of happiness is:",
output[3][0])
print("There were", output[3][1], "tweets counted. \n")
#determining and printing which region is the happiest
if output[0][0] > output[1][0] and output[0][0] > output[2][
0] and output[0][0] > output[3][0]:
print("The Eastern region is the happiest :D")
#
# Import compute_tweets function from "sentiment_analysis' module
from sentiment_analysis import compute_tweets
from string import punctuation
# Prompt user for the names of their tweet and keyword files
tweets = input("Enter tweet file: ")
keywords = input("Enter keyword file: ")
# Call the compute_tweets function with tweet and keyword files as parameters
result = compute_tweets(tweets, keywords)
print(result, "\n")
# Print results in readable format
if result != []:
print("Eastern Region: ")
print(" Happiness score: ", result[0][0])
print(" Number of keyword tweets: ", result[0][1])
print(" Total number of tweets: ", result[0][2], "\n")
print("Central Region: ")
print(" Happiness score: ", result[1][0])
print(" Number of keyword tweets: ", result[1][1])
print(" Total number of tweets: ", result[1][2], "\n")
print("Mountain Region: ")
print(" Happiness score: ", result[2][0])
print(" Number of keyword tweets: ", result[2][1])
print(" Total number of tweets: ", result[2][2], "\n")
#
# Driver for testing ... tests combinations of test files by calling call compute_tweets
#
from sentiment_analysis import compute_tweets
print()
print("** Test 1")
results = compute_tweets("tweets.txt", "keywords.txt")
print(results)
print()
print()
print("** Test 2")
results = compute_tweets("tweets1.txt", "key2.txt")
print(results)
print()
print()
print("** Test 3")
results = compute_tweets("tweets2.txt", "key1.txt")
print(results)
print()
print()
print("** Test 4")
results = compute_tweets("tweets2.txt", "key2.txt")
print(results)
print()
from sentiment_analysis import compute_tweets
tweetData = input("Enter the name of the file containing tweets: ")
keyData = input("Enter the name of the file containing Keywords: ")
results = compute_tweets(tweetData,keyData)
print("****************************************************")
print("Eastern:")
print("Average Happiness: {:.2f}".format(results[0][0]))
print("Number of Keyword Tweets: {}".format(results[0][1]))
print("Number of Tweets: {}".format(results[0][2]))
print("****************************************************")
print("Central:")
print("Average Happiness: {:.2f}".format(results[1][0]))
print("Number of Keyword Tweets: {}".format(results[1][1]))
print("Number of Tweets: {}".format(results[1][2]))
print("****************************************************")
print("Mountain:")
print("Average Happiness: {:.2f}".format(results[2][0]))
print("Number of Keyword Tweets: {}".format(results[2][1]))
print("Number of Tweets: {}".format(results[2][2]))
print("****************************************************")
print("Pacific:")
print("Average Happiness: {:.2f}".format(results[3][0]))
print("Number of Keyword Tweets: {}".format(results[3][1]))
print("Number of Tweets: {}".format(results[3][2]))
print("****************************************************")
