def test_analyze_bounds(self):
"""
Testing the bounds of the tweets values
"""
ana = Analyzer()
assert ana.analyze("this is a test neutral tweet") <= 1.0
assert ana.analyze("this is a test neutral tweet") >= 0.0
def test_analyze_bounds(self):
"""
Testing the bounds of the tweets values
"""
ana = Analyzer()
assert ana.analyze("this is a test neutral tweet") <= 1.0
assert ana.analyze("this is a test neutral tweet") >= 0.0
def testall(directory, pred_file=None, label_file=None, out_path=None):
folders = os.listdir(directory)
networks = []
for folder in folders:
if os.path.isfile(directory+folder+"/network.cfg") and os.path.exists(directory+folder+"/results"):
networks.append(folder)
config_file = directory+networks[0]+"/network.cfg"
config = ConfigParser.ConfigParser()
config.read(config_file)
test_data = LoadData(directory = config.get('Testing Data', 'folders').split(','),
data_file_name = config.get('Testing Data', 'data_file'),
label_file_name = config.get('Testing Data', 'label_file'),
seg_file_name = config.get('Testing Data', 'seg_file'))
res = Analyzer(raw = test_data.get_data()[0],
target = test_data.get_labels()[0])
for net in networks:
config_file = directory+net+"/network.cfg"
config = ConfigParser.ConfigParser()
config.read(config_file)
res.add_results(results_folder = config.get('General','directory'),
name = net,
prediction_file = config.get('Testing', 'prediction_file')+'_0',
learning_curve_file = 'learning_curve')
res.analyze(-1, pred_file=pred_file, label_file=label_file, out_path=out_path)
return res
def test_analyze_judgement_weight(self):
"""
Testing the value order
of arbitrary tweets
"""
ana = Analyzer()
assert ana.analyze("i am so happy, great day :D") > ana.analyze("i am so happy :D")
assert ana.analyze("so sad, feeling depressed :'(") < ana.analyze("so depressed :'(")
def test_analyze_empty(self):
"""
Testing empty tweets
and tweets including words not
in the dictionary
"""
ana = Analyzer()
assert ana.analyze("") == 0.5
assert ana.analyze("hzoehfsdl") == 0.5
def test_analyze_empty(self):
"""
Testing empty tweets
and tweets including words not
in the dictionary
"""
ana = Analyzer()
assert ana.analyze("") == 0.5
assert ana.analyze("hzoehfsdl") == 0.5
def test_analyze_judgement(self):
"""
Testing the proper judgement of the sentiment analysis:
* positive and negative
* best and worse tweet values
"""
ana = Analyzer()
assert ana.analyze(":)") > 0.5 and ana.analyze(":'(") < 0.5
assert ana.analyze("yahoo yahoo yahoo") == 1.0
assert ana.analyze("zzz zzz zzz zzz zzz") == 0.0
def test_categories_weight(self):
"""
Testing the weights of the different
categorie sums (positive, negative, neutral)
"""
ana = Analyzer()
ctg_total = {'positive': 0.0, 'negative': 0.0, 'neutral': 0.0}
ctg_count = {'positive': 4, 'negative': 2, 'neutral': 1}
data = [2, 3, 0, 2, 2, 0, -4, 0, 0, -2, 2]
tot_pos, tot_neg, tot_neu = ana.weight_categories(data, ctg_total, ctg_count)
assert (tot_pos, tot_neg, tot_neu) == (99.47646509317096, -49.392885301738836, 3.9750077625545726)
def test_categories_cardinality(self):
"""
Testing the cardinality of the different
categorie sums (positive, negative, neutral)
"""
ana = Analyzer()
ctg_count = {'positive': 0, 'negative': 0, 'neutral': 0}
text = 'great day today lol ;) but still have to work'
assert ana.categories_cardinality(text, ctg_count) == 15
assert ctg_count['positive'] == 4 # great day lol ;)
assert ctg_count['neutral'] == 1 # today
assert ctg_count['negative'] == 2 # work still
def test_categories_cardinality(self):
"""
Testing the cardinality of the different
categorie sums (positive, negative, neutral)
"""
ana = Analyzer()
ctg_count = {'positive': 0, 'negative': 0, 'neutral': 0}
text = 'great day today lol ;) but still have to work'
assert ana.categories_cardinality(text, ctg_count) == 15
assert ctg_count['positive'] == 4 # great day lol ;)
assert ctg_count['neutral'] == 1 # today
assert ctg_count['negative'] == 2 # work still
def test_categories_weight(self):
"""
Testing the weights of the different
categorie sums (positive, negative, neutral)
"""
ana = Analyzer()
ctg_total = {'positive': 0.0, 'negative': 0.0, 'neutral': 0.0}
ctg_count = {'positive': 4, 'negative': 2, 'neutral': 1}
data = [2, 3, 0, 2, 2, 0, -4, 0, 0, -2, 2]
tot_pos, tot_neg, tot_neu = ana.weight_categories(
data, ctg_total, ctg_count)
assert (tot_pos, tot_neg,
tot_neu) == (99.47646509317096, -49.392885301738836,
3.9750077625545726)
def testprediction(config_file, pred_file=None, label_file=None, out_path=None):
config = ConfigParser.ConfigParser()
config.read(config_file)
test_data = LoadData(directory = config.get('Testing Data', 'folders').split(','),
data_file_name = config.get('Testing Data', 'data_file'),
label_file_name = config.get('Testing Data', 'label_file'),
seg_file_name = config.get('Testing Data', 'seg_file'))
res = Analyzer(raw = test_data.get_data()[0],
target = test_data.get_labels()[0])
res.add_results(results_folder = config.get('General','directory'),
name = config_file.split('/')[-3],
prediction_file = config.get('Testing', 'prediction_file')+'_0',
learning_curve_file = 'learning_curve')
res.analyze(-1, pred_file=pred_file, label_file=label_file, out_path=out_path)
return res
def analyze(chart_ids: List[str] = [],
src: str = CHART_PATH,
dest: str = default_excel_path):
"""
Analyzes charts given a list of IDs. If you want to analyze all levels
in src, don't input any IDs.
"""
if len(chart_ids) == 0:
with os.scandir(src) as dir_items:
chart_ids = [
cid.name for cid in dir_items if is_chart_folder(cid.path)
]
if len(chart_ids) == 0:
click.echo("No charts in the folder!")
stat_list = dict()
src = os.path.abspath(src)
dest = os.path.abspath(dest)
os.makedirs(os.path.dirname(dest), exist_ok=True)
with click.progressbar(chart_ids,
label=f"Analyzing {len(chart_ids)} charts...",
item_show_func=lambda x: x) as prog_bar:
for chart_id in prog_bar:
analyzer = Analyzer(src, chart_id)
analyzer.start()
stats = analyzer.get_stats_as_json()
stat_list[chart_id] = stats
click.echo(f"Done analyzing, now saving to {dest}...")
dest_folder = os.path.dirname(dest)
os.makedirs(dest_folder, exist_ok=True)
stat_df = pd.DataFrame.from_dict(stat_list, orient="index")
stat_df.index.name = "chart_id"
excel_writer = ExcelWriter(stat_df, dest)
excel_writer.format_table()
excel_writer.close()
click.echo("Stats successfully saved.")
def home():
if request.method == 'GET':
# render homepage template
return render_template('boot.html')
else:
# grab POST form data
data = request.form
# parse as JSON
jsondata = json.dumps(data, separators=(',', ':'))
if 'topic' in jsondata:
# load data into dictionary
new_data = json.loads(jsondata)
# create random number for this graph
new_data['rand'] = str(int(random.random() * 999999999))
# connect to twitter
auth = OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
api = tweepy.API(auth)
# get the tweets
tweets = stream.gather_tweets(
api, auth, keyword=new_data['topic'][0],
limit=int(new_data['limit'][0]))
# Create analyzer
analyzer = Analyzer(tweets, new_data['topic'][0])
analyzer.save_sentiment_data(int(new_data['rand']))
# render results page
return redirect((url_for('log', data=json.dumps(new_data),
mode='debug')))
elif 'username' in jsondata:
# load data into dictionary
new_data = json.loads(jsondata)
# create random number for this graph
new_data['rand'] = str(int(random.random() * 999999999))
# connect to twitter
auth = OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
api = tweepy.API(auth)
# get the tweets
tweets = stream.gather_tweets(
api, auth, username=new_data['username'][0], limit=50)
# Create analyzer
analyzer = Analyzer(tweets, new_data['username'][0])
analyzer.save_sentiment_data(int(new_data['rand']))
return redirect((url_for('log', data=json.dumps(new_data),
mode='debug')))
def test_analyze_judgement(self):
"""
Testing the proper judgement of the sentiment analysis:
* positive and negative
* best and worse tweet values
"""
ana = Analyzer()
assert ana.analyze(":)") > 0.5 and ana.analyze(":'(") < 0.5
assert ana.analyze("yahoo yahoo yahoo") == 1.0
assert ana.analyze("zzz zzz zzz zzz zzz") == 0.0
def test_analyze_judgement_weight(self):
"""
Testing the value order
of arbitrary tweets
"""
ana = Analyzer()
assert ana.analyze("i am so happy, great day :D") > ana.analyze(
"i am so happy :D")
assert ana.analyze("so sad, feeling depressed :'(") < ana.analyze(
"so depressed :'(")
def ViewResults(**kwargs):
directory = kwargs.get("directory", "")
network = kwargs.get("network", None)
prediction_file = kwargs.get("predictions_file", None)
if network:
# Assume that all networks are tested on the same set of data
config = ConfigParser.ConfigParser()
config.read("networks/" + network + "/network.cfg")
data = LoadData(
directory=config.get("Testing Data", "folders").split(",")[0],
data_file_name=config.get("Testing Data", "data_file"),
label_file_name=config.get("Testing Data", "label_file"),
)
if not prediction_file:
prediction_file = "test_prediction_0"
results = Analyzer(target=data.get_labels()[0], raw=data.get_data()[0])
results.add_results(results_folder="networks/" + network + "/", name=network, prediction_file=prediction_file)
else:
folders = os.listdir(directory)
networks = []
for folder in folders:
if os.path.isfile(directory + folder + "/network.cfg"):
networks.append(folder)
# Assume that all networks are tested on the same set of data
config = ConfigParser.ConfigParser()
config.read(directory + networks[0] + "/network.cfg")
data = LoadData(
directory=config.get("Testing Data", "folders").split(",")[0],
data_file_name=config.get("Testing Data", "data_file"),
label_file_name=config.get("Testing Data", "label_file"),
)
if not prediction_file:
prediction_file = "test_prediction_0"
results = Analyzer(target=data.get_labels()[0], raw=data.get_data()[0])
for net in networks:
results.add_results(results_folder=directory + net + "/", name=net, prediction_file=prediction_file)
return results
h = TweetLoader('', path='data/backup/', filename='hillary_2016-07-13.json')
t = TweetLoader('', path='data/backup/', filename='trump_2016-07-13.json')
h.load()
t.load()
# Join them together
full_tweets = pd.concat([h.tweets, t.tweets])
# Assign label (second array) for Hillary(0)/Trump(1) tweets
label_array = np.array([0] * len(h.tweets) + [1] * len(t.tweets))
# Run through part of the model to get the PCA results and loading factors
# This is not the full model, just a part of it for illustration purposes
max_words = 50
mod = Analyzer(full_tweets['text'],
labels=label_array,
max_words=max_words,
load_pca=False)
# mod.load_words()
mod.get_words()
mod.create_dtm()
mod.run_pca()
loadings = mod.loadings
loadings.index = ['PC' + str(j + 1) for j in range(len(loadings))]
# loadings = loadings.iloc[0:30, :] # Use only a subset of the data
loadings = loadings.transpose() # Use rotation
words = loadings.columns.tolist()
pc_names = loadings.index.tolist()
# t = TweetLoader('realDonaldTrump')
h = TweetLoader('', path='data/backup/', filename='hillary_2016-07-13.json')
t = TweetLoader('', path='data/backup/', filename='trump_2016-07-13.json')
h.load()
t.load()
# Join them together
full_tweets = pd.concat([h.tweets, t.tweets])
# Assign label (second array) for Hillary(0)/Trump(1) tweets
label_array = np.array([0]*len(h.tweets) + [1]*len(t.tweets))
# Run through part of the model to get the PCA results and loading factors
# This is not the full model, just a part of it for illustration purposes
max_words = 50
mod = Analyzer(full_tweets['text'], labels=label_array, max_words=max_words, load_pca=False)
# mod.load_words()
mod.get_words()
mod.create_dtm()
mod.run_pca()
loadings = mod.loadings
loadings.index = ['PC'+str(j+1) for j in range(len(loadings))]
# loadings = loadings.iloc[0:30, :] # Use only a subset of the data
loadings = loadings.transpose() # Use rotation
words = loadings.columns.tolist()
pc_names = loadings.index.tolist()
import matplotlib.pyplot as plt
# Load tweets
s2 = TweetLoader(filename='coolstars.json',
track_location=False,
path='coolstars19/data/')
s2.load()
df = s2.tweets.copy()
df.index = pd.DatetimeIndex(df['created_at'])
# Using the Analyzer class
max_words = 100
mod = Analyzer(df['text'],
None,
max_words=max_words,
load_pca=False,
load_svm=False,
more_stop_words=['rt', 'cs19', 'cs19_uppsala'])
mod.get_words()
mod.create_dtm()
mod.run_pca()
# Exploration
print_dtm(mod.dtm, df['text'], 42)
# Top terms in components
top_factors(mod.load_squared, 0)
# Plots
make_biplot(mod.pcscores, None, mod.loadings, 0, 1)
print("Unknown model " + args.model + ".\n")
exit()
# Send model weights to the device
model.to(args.device)
print(model)
#%%
"""
###################
Initialize model and analyzer save
###################
"""
# Apply weight initialization
model.apply(initializer)
# Create an analyzer object
analyzer = Analyzer(args)
#%%
"""
###################
Create optimizer
###################
"""
# Optimizer and Loss
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr, weight_decay=1e-4)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
factor=0.5,
threshold=1e-6)
# Use cross-entropy loss
if args.model in ['ae', 'vae', 'wae', 'vae_flow']:
criterion = nn.L1Loss()
def main(argv=None):
#read in params
if argv is None:
argv = sys.argv[1:]
file = 'tulalens_survey_sample.csv'
facet = 'result id'
#standard python parsing for command line options
opts = []
args = []
try:
opts, args = getopt.getopt(argv, "hl", ["help", "list", "file=", "facet="])
except getopt.GetoptError as msg:
print(sys.stderr, msg)
print >>sys.stderr, "For help use --help"
return 2
if len(args):
print >>sys.stderr, "Invalid arg(s) %s"%args
usage()
return 2
for (opt, val) in opts:
if opt in ("-h", "--help"):
usage()
return 0
if opt in ("-l", "--list"):
list()
return 0
elif opt in ("--file"):
file = val
elif opt in ("--facet"):
facet = val.lower()
else:
usage()
return 2
print("facet: %s" % facet)
#check if facet given is in the list of survey questions
#ideally this allows for quick entries with just the
#question number, e.g. "--facet Q30"
long_q = '' #keep track of the long form for later use
valid_facet = False
for long, short in SHORT_QUESTIONS.items():
#print("checking question: %s" % question)
if facet in long:
#turn the facet into easy to use question ids
#p = "(^q\d\d?[.]).*"
#m = re.match(p, long)
facet = short
long_q = long
print("Question selected: %s" % long_q)
valid_facet = True
break
if not valid_facet:
sys.exit("facet selected is not a survey question")
#parse csv file
parser = CsvParse(file)
answers = parser.parse()
#generate analysis based on options
#print("number of answer rows after parse: %s" % len(answers))
analyze = Analyzer(answers)
#find the unique occurrence of each answer to the question
answers_count = analyze.group_by(facet)
mean = analyze.find_mean(facet, answers_count)
sys.exit()
from analysis import Analyzer
from helper_functions import print_dtm, top_factors, make_biplot
import pandas as pd
import matplotlib.pyplot as plt
# Load tweets
s2 = TweetLoader(filename='coolstars.json', track_location=False, path='coolstars19/data/')
s2.load()
df = s2.tweets.copy()
df.index = pd.DatetimeIndex(df['created_at'])
# Using the Analyzer class
max_words = 100
mod = Analyzer(df['text'], None, max_words=max_words, load_pca=False, load_svm=False,
more_stop_words=['rt', 'cs19', 'cs19_uppsala'])
mod.get_words()
mod.create_dtm()
mod.run_pca()
# Exploration
print_dtm(mod.dtm, df['text'], 42)
# Top terms in components
top_factors(mod.load_squared, 0)
# Plots
make_biplot(mod.pcscores, None, mod.loadings, 0, 1)
404 error handler
used if a non existant route
is requested
"""
return render_template('404.html'), 404
@app.errorhandler(500)
def page_not_found(exc):
"""
500 error handler
used if there is a server error
"""
return render_template('500.html'), 500
if __name__ == '__main__':
analyzer = Analyzer()
server = SocketIOServer(('', PORT), app, resource="socket.io")
tw_thread = TweetWeather(server, analyzer, name="Tweet-Weather-Thread")
tw_thread.daemon = True
gevent.spawn(tw_thread.new_post, server)
gevent.spawn(tw_thread.connexion_lost, server)
print "Application Started: http://localhost:5000"
try:
server.serve_forever()
except KeyboardInterrupt:
tw_thread.stop()
server.stop()
sys.exit()
# Merge tweets together, pass to Analyzer
df_tweets = pd.concat([h.tweets['text'], t.tweets['text']],
axis=0,
join='outer',
join_axes=None,
ignore_index=True,
keys=None,
levels=None,
names=None,
verify_integrity=False)
# Using the Analyzer class
mod = Analyzer(df_tweets,
label_array,
max_words=max_words,
load_pca=False,
load_svm=False,
use_sentiment=True)
# mod.get_words()
# mod.create_dtm()
# mod.run_pca()
# mod.get_sentiment()
# test_predict, test_label = mod.run_svm()
# One-line alternative with defaults
test_predict, test_label = mod.create_full_model()
# Check a PCA plot
# mod.make_biplot(2, 3, max_arrow=0.2)
def __init__(self, market):
super(MarketThread, self).__init__()
self.market = market
def run(self):
while not self._stop.isSet():
time.sleep(settings.HEARTBEAT)
self.market.update()
if __name__ == "__main__":
q = Queue.Queue()
p = Portfolio(20000)
e = Executor(p)
a = Analyzer(portfolio=p)
m = Market(queue=q)
trading_thread = TradingThread(queue=q, analyzer=a, events=e)
market_thread = MarketThread(market=m)
def receive_signal(signum, stack):
print("You quit")
trading_thread.stop()
market_thread.stop()
sys.exit(0)
market_thread.start()
trading_thread.start()
signal.signal(signal.SIGINT, receive_signal)
print(tweet.text.encode('utf-8'))
tweets.append(tweet._json)
count += 1
if count > limit:
break
return tweets
elif keyword:
l = StdOutListener()
stream = Stream(auth, l)
global lim
lim = limit
stream.filter(track=[keyword])
with open('tweet_stream.pickle', 'rb') as f:
return pickle.load(f)
else:
raise ValueError('Invalid Arguments. username and keyword both' +
'can\'t be None')
if __name__ == '__main__':
s = 'baltimore'
auth = OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
api = tweepy.API(auth)
# tweets = gather_tweets(username=s) # last 30 tweets
tweets = gather_tweets(keyword=s, limit=30)
# Create analyzer
analyzer = Analyzer(tweets, s)
avg = analyzer.calc_sentiment()
#keywrds = analyzer.get_keywords()
analyzer.save_sentiment_data()
# timer
STOP = time.time()
print(f"\t-----> Done.")
print(f"\t-----> Execution time: {round(STOP-START, 2)} sec")
if __name__ == "__main__":
app_settings = {
'client_id': os.getenv('SPOTIFY_CLIENT_ID'),
'client_secret': os.getenv('SPOTIFY_CLIENT_SECRET'),
'redirect_uri': os.getenv('SPOTIFY_REDIRECT_URI')
}
# init analyzer
az = Analyzer(**app_settings)
# get tracks and simulate lengths
# get all playlists
playlists = az.user_playlists(is_author=True)
start = time.time()
print("-----> Gathering all tracks...", end="")
# get all tracks
all_tracks = []
for playlist in playlists:
tracks = az.playlist_tracks(playlist['id'])
# append the playlist meta data
# to the track objects
for i in range(len(tracks)):
tracks[i]['playlist'] = playlist
# h = TweetLoader('HillaryClinton')
# t = TweetLoader('realDonaldTrump')
h = TweetLoader('', path='data/backup/', filename='hillary_2016-07-13.json')
t = TweetLoader('', path='data/backup/', filename='trump_2016-07-13.json')
h.load()
t.load()
# Assign label (second array) for Hillary(0)/Trump(1) tweets
label_array = np.array([0]*len(h.tweets) + [1]*len(t.tweets))
# Merge tweets together, pass to Analyzer
df_tweets = pd.concat([h.tweets['text'], t.tweets['text']], axis=0, join='outer', join_axes=None,
ignore_index=True, keys=None, levels=None, names=None, verify_integrity=False)
# Using the Analyzer class
mod = Analyzer(df_tweets, label_array, max_words=max_words, load_pca=False, load_svm=False, use_sentiment=True)
# mod.get_words()
# mod.create_dtm()
# mod.run_pca()
# mod.get_sentiment()
# test_predict, test_label = mod.run_svm()
# One-line alternative with defaults
test_predict, test_label = mod.create_full_model()
# Check a PCA plot
# mod.make_biplot(2, 3, max_arrow=0.2)
# Check results
cm = mod.make_confusion_matrix(test_label, test_predict, normalize=False, axis=0, label_names=['Clinton', 'Trump'])
"pem_name",
help=
"Name of the PEM file that is needed to connect to the data collection servers."
)
parser.add_argument(
"database_ip",
help="IP of the Postgres database that the results will be put into.")
parser.add_argument("data_collector_ips",
nargs='+',
help="List of IPs of the data collection servers.")
args = parser.parse_args()
ec = External_Connector(args.pem_name, args.database_ip)
# Create list of local files, first is twitter data, rest is news data
files = [
"%s%d.txt" % (args.type, i) for i in range(0, len(args.data_collector_ips))
]
ec.get_data_files(args.data_collector_ips, files)
a = Analyzer()
# Run three analyses for each data file and upload them to database
for f in files:
sentiment, mood, emoticon = a.run(args.type, f)
ec.insert_sentiment(args.run_id, args.type, sentiment)
ec.insert_mood(args.run_id, args.type, mood)
ec.insert_emoticon(args.run_id, args.type, emoticon)
import pandas as pd
import numpy as np
# Some global defaults
max_words = 200
# Load most recent tweets from Hillary Clinton and Donald Trump
# s = TweetLoader(filename='search.json', track_location=True)
s = TweetLoader(filename='search_2016-07-13.json',
track_location=True,
path='data/backup/')
s.load()
# Calculate and grab model results
mod = Analyzer(s.tweets['text'],
max_words=max_words,
load_pca=True,
load_svm=True)
predict = mod.load_full_model() # Hillary=0 Trump=1
s.tweets['predict'] = predict
# Clean up missing coordinates
df = s.tweets['geo.coordinates']
bad = df.apply(lambda x: x is None)
df = df[~bad]
s.tweets = s.tweets[~bad]
lat = df.apply(lambda x: x[0])
lon = df.apply(lambda x: x[1])
# lat, lon = zip(*df) # Alternate
# Remove Alaska and Hawaii
def main(argv=None):
#read in params
if argv is None:
argv = sys.argv[1:]
file = 'tulalens_survey_sample.csv'
facet = 'result id'
#standard python parsing for command line options
opts = []
args = []
try:
opts, args = getopt.getopt(argv, "hl",
["help", "list", "file=", "facet="])
except getopt.GetoptError as msg:
print(sys.stderr, msg)
print >> sys.stderr, "For help use --help"
return 2
if len(args):
print >> sys.stderr, "Invalid arg(s) %s" % args
usage()
return 2
for (opt, val) in opts:
if opt in ("-h", "--help"):
usage()
return 0
if opt in ("-l", "--list"):
list()
return 0
elif opt in ("--file"):
file = val
elif opt in ("--facet"):
facet = val.lower()
else:
usage()
return 2
print("facet: %s" % facet)
#check if facet given is in the list of survey questions
#ideally this allows for quick entries with just the
#question number, e.g. "--facet Q30"
long_q = '' #keep track of the long form for later use
valid_facet = False
for long, short in SHORT_QUESTIONS.items():
#print("checking question: %s" % question)
if facet in long:
#turn the facet into easy to use question ids
#p = "(^q\d\d?[.]).*"
#m = re.match(p, long)
facet = short
long_q = long
print("Question selected: %s" % long_q)
valid_facet = True
break
if not valid_facet:
sys.exit("facet selected is not a survey question")
#parse csv file
parser = CsvParse(file)
answers = parser.parse()
#generate analysis based on options
#print("number of answer rows after parse: %s" % len(answers))
analyze = Analyzer(answers)
#find the unique occurrence of each answer to the question
answers_count = analyze.group_by(facet)
mean = analyze.find_mean(facet, answers_count)
sys.exit()
from bokeh.sampledata.us_states import data as states from bokeh.models import ColumnDataSource, HoverTool import reverse_geocoder as rg import pandas as pd import numpy as np # Some global defaults max_words = 200 # Load most recent tweets from Hillary Clinton and Donald Trump # s = TweetLoader(filename='search.json', track_location=True) s = TweetLoader(filename='search_2016-07-13.json', track_location=True, path='data/backup/') s.load() # Calculate and grab model results mod = Analyzer(s.tweets['text'], max_words=max_words, load_pca=True, load_svm=True) predict = mod.load_full_model() # Hillary=0 Trump=1 s.tweets['predict'] = predict # Clean up missing coordinates df = s.tweets['geo.coordinates'] bad = df.apply(lambda x: x is None) df = df[~bad] s.tweets = s.tweets[~bad] lat = df.apply(lambda x: x[0]) lon = df.apply(lambda x: x[1]) # lat, lon = zip(*df) # Alternate # Remove Alaska and Hawaii del states["HI"]
___author__ = 'Ahmed Hani Ibrahim' from reader import DataReader from analysis import Analyzer file_path = './data/data_science_dataset_wuzzuf.csv' reader = DataReader(file_path) data = reader.read_data() analyzer = Analyzer(data) analyzer.trending_category() x = 0
import matplotlib.pyplot as plt
import seaborn as sns
sys.path.insert(1, "../tools")
from analysis import Analyzer
from plotting import Plotter
from training import Trainer
if __name__ == "__main__":
sns.set()
plot_dir = "plots"
plot_file = os.path.join(plot_dir, "rdf.png")
if not os.path.exists(plot_dir):
os.mkdir(plot_dir)
anl = Analyzer()
plter = Plotter()
r_cut = 6.0
r, rdf = anl.calculate_rdf("trajs/training.traj", r_max=r_cut)
rdf[np.nonzero(rdf)] /= max(rdf)
cutoff = plter.polynomial(r, r_cut, gamma=5.0)
plt.plot(r, rdf, label="Radial distribution function")
plt.plot(r, cutoff, label="Polynomial cutoff, gamma=5.0")
plt.legend()
plt.title("Copper radial distribution function")
plt.xlabel("Radial distance [Angstrom]")
plt.ylabel("Radial distribution function (normalized to 1)")
plt.savefig(plot_file)
trn.create_Gs(elements, num_radial_etas, num_angular_etas, num_zetas,
angular_type)
symm_funcs["Selected"] = trn.Gs
G2 = make_symmetry_functions(elements=elements,
type="G2",
etas=[0.05, 0.23, 1.0, 5.0],
centers=np.zeros(4))
G4 = make_symmetry_functions(
elements=elements,
type="G4",
etas=0.005 * np.ones(1),
zetas=[1.0, 4.0],
gammas=[1.0, -1.0],
)
symm_funcs["Default"] = G2 + G4
anl = Analyzer()
plter = Plotter()
r, rdf = anl.calculate_rdf(train_traj, r_max=cutoff.Rc)
for label, symm_func in symm_funcs.items():
plter.plot_symmetry_functions(
label + "_rad.png",
label + "_ang.png",
symm_func,
rij=r,
rdf=rdf,
cutoff=cutoff,
)
def analyze(self, expr):
name = "f"
self.analyzer = Analyzer(expr)
self.function_view.set_from_expression(expr, name=name + "(x)")
self.function_view.set_font_size(40)
box = ListBox("Dominio")
self.box.pack_start(box, False, False, 0)
domain_block = EqualBlock(TextBlock("D(f)"), TextBlock(interval_to_string(self.analyzer.domain)))
box.make_row_with_child(domain_block)
box = ListBox("Raíces")
self.box.pack_start(box, False, False, 0)
roots_block = TextBlock(set_to_string(self.analyzer.roots.keys()))
box.make_row_with_child(roots_block)
box = ListBox("Signo")
self.box.pack_start(box, False, False, 0)
if self.analyzer.positive.__class__ != sympy.EmptySet:
positive_block = TextBlock("+ " + interval_to_string(self.analyzer.positive))
box.make_row_with_child(positive_block)
if self.analyzer.negative.__class__ != sympy.EmptySet:
negative_block = TextBlock("- " + interval_to_string(self.analyzer.negative))
box.make_row_with_child(negative_block)
box = ListBox("Continuidad")
self.box.pack_start(box, False, False, 0)
if self.analyzer.continuity == self.analyzer.domain:
block = TextBlock("f es continua en todo su dominio.")
else:
block = TextBlock("f es continua para los x %s %s\n" % (Chars.BELONGS, interval_to_string(self.analyzer.continuity)))
box.make_row_with_child(block)
box = ListBox("Ramas")
self.box.pack_start(box, False, False, 0)
if self.analyzer.branches[sympy.oo] is not None:
block = TextBlock("f posee %s cuando" % Branch.get_name(*self.analyzer.branches[sympy.oo]))
row = box.make_row_with_child(block)
trend_block = TrendBlock(TextBlock("x"), TextBlock("+" + Chars.INFINITY))
trend_block.set_margin_left(10)
row.add_child(trend_block)
if self.analyzer.branches[-sympy.oo] is not None:
block = TextBlock("f posee %s cuando" % Branch.get_name(*self.analyzer.branches[-sympy.oo]))
row = box.make_row_with_child(block)
trend_block = TrendBlock(TextBlock("x"), TextBlock("-" + Chars.INFINITY))
trend_block.set_margin_left(10)
row.add_child(trend_block)
box = ListBox("Crecimiento")
self.box.pack_start(box, False, False, 0)
block = MathView.new_from_expression(self.analyzer.derived, name + "'(x)")
box.make_row_with_child(block)
if self.analyzer.derived_things.negative.__class__ != sympy.EmptySet:
block = TextBlock(name + " decrece en ")
row = box.make_row_with_child(block)
row.add_child(make_interval_points(self.analyzer.derived_things.negative))
if self.analyzer.derived_things.positive.__class__ != sympy.EmptySet:
block = TextBlock(name + " crece en ")
row = box.make_row_with_child(block)
row.add_child(make_interval_points(self.analyzer.derived_things.positive))
mins, maxs = self.analyzer.get_minimums_and_maximums()
if mins:
block = TextBlock("Mínimos: ")
row = box.make_row_with_child(block)
for point in mins:
_x = MathView.new_from_expression(point[0])
_y = MathView.new_from_expression(point[1])
block = PointBlock(_x, _y)
row.add_child(block)
if maxs:
block = TextBlock("Máximos: ")
row = box.make_row_with_child(block)
for point in maxs:
_x = MathView.new_from_expression(point[0])
_y = MathView.new_from_expression(point[1])
block = PointBlock(_x, _y)
row.add_child(block)
box = ListBox("Concavidad")
self.box.pack_start(box, False, False, 0)
block = MathView.new_from_expression(self.analyzer.derived2, name + "''(x)")
box.make_row_with_child(block)
if self.analyzer.derived2_things.positive.__class__ != sympy.EmptySet:
block = TextBlock("f tiene concavidad positiva en: ")
row = box.make_row_with_child(block)
row.add_child(make_interval_points(self.analyzer.derived2_things.positive))
if self.analyzer.derived2_things.negative.__class__ != sympy.EmptySet:
block = TextBlock("f tiene concavidad negativa en: ")
row = box.make_row_with_child(block)
row.add_child(make_interval_points(self.analyzer.derived2_things.negative))
_analyzer = Analyzer(self.analyzer.derived)
mins, maxs = _analyzer.get_minimums_and_maximums()
inflection_points = mins + maxs
if inflection_points:
block = TextBlock("Puntos de inflexión: ")
row = box.make_row_with_child(block)
for point in inflection_points:
_x = MathView.new_from_expression(point[0])
_y = MathView.new_from_expression(point[1])
block = PointBlock(_x, _y)
block.set_margin_right(10)
row.add_child(block)
self.show_all()
test_traj = "test.traj"
steps, test_traj = trjbd.integrate_atoms(
test_atoms, test_traj, n_test, save_interval, timestep=timestep, convert=True
)
amp_test_traj = "amp_test.traj"
steps, amp_test_traj = trjbd.integrate_atoms(
amp_test_atoms,
amp_test_traj,
n_test,
save_interval,
timestep=timestep,
convert=True,
)
anl = Analyzer()
r, rdf = anl.calculate_rdf(test_traj, r_max=6.0)
r_amp, rdf_amp = anl.calculate_rdf(amp_test_traj, r_max=6.0)
rdf_plot = system + "_" + "rdf.png"
plter.plot_rdf(rdf_plot, legend, r, rdf, rdf_amp)
steps, energy_exact, energy_amp = anl.calculate_pot_energy_diff(
test_traj, amp_test_traj, save_interval=save_interval
)
pot_plot = system + "_" + "pot.png"
plter.plot_pot_energy_diff(pot_plot, legend, steps, energy_exact, energy_amp)
steps, energy_exact, energy_amp = anl.calculate_energy_diff(
test_traj, amp_test_traj, save_interval=save_interval
)
energy_plot = system + "_" + "energy.png"
# h = TweetLoader('HillaryClinton')
# t = TweetLoader('realDonaldTrump')
h = TweetLoader('', path='data/backup/', filename='hillary_2016-07-13.json')
t = TweetLoader('', path='data/backup/', filename='trump_2016-07-13.json')
h.load()
t.load()
# Assign label (second array) for Hillary(0)/Trump(1) tweets
label_array = np.array([0]*len(h.tweets) + [1]*len(t.tweets))
df_tweets = pd.concat([h.tweets['text'], t.tweets['text']], axis=0, join='outer', join_axes=None,
ignore_index=True, keys=None, levels=None, names=None, verify_integrity=False)
# Using the Analyzer class to get sentiments
mod = Analyzer(df_tweets, label_array)
mod.get_sentiment()
# Group together tweets, labels, and sentiments
temp = pd.concat([h.tweets, t.tweets], axis=0, join='outer', join_axes=None, ignore_index=True, levels=None)
df = pd.concat([temp, mod.sentiment, pd.DataFrame({'label': label_array})], axis=1, levels=None)
# Get Tweet text and URLs for embedding: https://twitter.com/{user}/status/{id}
def print_and_get_url(tweet):
print tweet['text'].values[0]
print 'https://twitter.com/{}/status/{}'.format(tweet['user.screen_name'].values[0], tweet['id'].values[0])
# Most positive and negative tweet
print_and_get_url(df.sort_values(by='positive', ascending=False)[df['label'] == 0])
print_and_get_url(df.sort_values(by='positive', ascending=False)[df['label'] == 1])
# Assign label (second array) for Hillary(0)/Trump(1) tweets
label_array = np.array([0] * len(h.tweets) + [1] * len(t.tweets))
df_tweets = pd.concat([h.tweets['text'], t.tweets['text']],
axis=0,
join='outer',
join_axes=None,
ignore_index=True,
keys=None,
levels=None,
names=None,
verify_integrity=False)
# Using the Analyzer class to get sentiments
mod = Analyzer(df_tweets, label_array)
mod.get_sentiment()
# Group together tweets, labels, and sentiments
temp = pd.concat([h.tweets, t.tweets],
axis=0,
join='outer',
join_axes=None,
ignore_index=True,
levels=None)
df = pd.concat([temp, mod.sentiment,
pd.DataFrame({'label': label_array})],
axis=1,
levels=None)