示例#1
0
def print_chart(top):
    """
    param top: a list of (word, count) tuples.
    """
    if args.html:
        print("<ol>")

    for i, (word, count) in enumerate(top):
        if args.html:
            print("<li>{0} ({1})</li>".format(word, commafy(count)))
        else:
            print(str(i+1) + ". " + word + " (" + commafy(count) + ")")

    if args.html:
        print("</ol>")
示例#2
0
def filter_word(tweets, desired_word):
    found = []
    for tweet in tweets:
        if desired_word == tweet["word"]:
            found.append(tweet)
    print("Total " + desired_word + ":\t" + commafy(len(found)))
    return found
示例#3
0
def filter_search_term(tweets, desired_search_term):
    found = []
    for tweet in tweets:
        if desired_search_term in tweet["search_term"]:
            found.append(tweet)
    print("Total " + desired_search_term + ":\t" + commafy(len(found)))
    return found
示例#4
0
def filter_word(tweets, desired_word):
    found = []
    for tweet in tweets:
        if desired_word == tweet["word"]:
            found.append(tweet)
    print("Total " + desired_word + ":\t" + commafy(len(found)))
    return found
示例#5
0
def filter_year(tweets, desired_year):
    found = []
    for tweet in tweets:
        year = int(tweet["created_at"][-4:])
        if desired_year == year:
            found.append(tweet)
    print("Total in " + str(desired_year) + ":\t" + commafy(len(found)))
    return found
示例#6
0
    )
    parser.add_argument("-c", "--csv", default="M:/bin/data/all.csv", help="Input CSV file")
    parser.add_argument("-w", "--word", default="bae", help="Word to search for")
    parser.add_argument("-y", "--year", type=int, default=None, help="Only from this year")
    parser.add_argument("-s", "--search_term", help="Only for this search term")
    parser.add_argument(
        "-p",
        "--plot",
        action="store_true",
        help="Create a bar graph of results (requires Plotly authentication: "
        "https://plot.ly/python/getting-started/",
    )
    args = parser.parse_args()

    tweets = load_csv(args.csv)
    print("Total tweets:\t" + commafy(len(tweets)))

    tweets = filter_word(tweets, args.word)

    if args.search_term:
        tweets = filter_search_term(tweets, args.search_term)

    if args.year:
        tweets = filter_year(tweets, args.year)

    # Sort by ID = sort chronologically
    tweets = sorted(tweets, key=lambda k: k["id_str"])

    xs, ys = print_per_month(tweets)

    if args.plot:
示例#7
0
    parser.add_argument(
        '-y', '--year',  type=int, default=None,
        help="Only from this year")
    parser.add_argument(
        '-s', '--search_term',
        help="Only for this search term")
    parser.add_argument(
        '--diff', action='store_true',
        help="Compare a year to the previous year")
    parser.add_argument(
        '--html', action='store_true',
        help="Output with html markup")
    args = parser.parse_args()

    tweets = load_csv(args.csv)
    print("Total tweets:\t" + commafy(len(tweets)))

    if args.diff and args.year:
        last_year = print_top(tweets, number=args.top_number, year=args.year-1,
                              search_term=args.search_term)
        this_year = print_top(tweets, number=args.top_number, year=args.year,
                              search_term=args.search_term)
        last_years_words = [e[0] for e in last_year]
        this_years_words = [e[0] for e in this_year]

        set1 = set(last_years_words)
        diff = [x for x in this_years_words if x not in set1]

        top = []
        for word in diff:
            for e in this_year: