def graph(id):
project = Project.query.get_or_404(id)
logs = project.logs
log_number = len([1 for _ in logs])
if project.logs and log_number > 1:
logs = project.logs.order_by(ProjectLog.log_date)
x = [
datetime.combine(log.log_date, datetime.min.time()).timestamp() *
1000 for log in logs
]
y = [log.previous_score * score_multiplier for log in logs]
multi_iter = {'x': x, 'data': y}
line = vincent.Line(multi_iter, iter_idx='x')
line.scales['x'] = vincent.Scale(name='x',
type='time',
range='width',
domain=vincent.DataRef(
data='table', field="data.idx"))
line.scales['y'] = vincent.Scale(name='y',
range='height',
nice=True,
domain=[0, score_multiplier])
line.scales['color'] = vincent.Scale(name='color',
range=['#12897D'],
type='ordinal')
line.axes['y'].ticks = 3
line.axes['x'].ticks = 7
if line_style:
line.marks['group'].marks[
0].properties.enter.interpolate = vincent.ValueRef(
value=line_style)
return jsonify({"status": "success", "data": line.grammar()})
else:
return failure_response("No history for this project", 404)
def plotrwresult(G):
visits = [G.node[node]['visits'] for node in G.nodes_iter()]
norm_visits = np.array(visits) / float(G.graph['total_visits'])
deaths = [G.node[node]['deaths'] for node in G.nodes_iter()]
norm_deaths = np.array(deaths) / float(sum(deaths))
if G.is_directed():
degrees = [G.in_degree(node) for node in G.nodes_iter()]
norm_degrees = np.array(degrees) / float(G.size())
else:
degrees = [G.degree(node) for node in G.nodes_iter()]
aorm_degrees = np.array(degrees) / float(2 * G.size())
multi_iter1 = {
'index': range(G.order()),
'Visits': norm_visits,
'Deaths': norm_deaths,
'Degree': norm_degrees
}
line = vincent.Scatter(multi_iter1, iter_idx='index')
line.axis_titles(x='Vertex', y='Juice')
line.legend(title='Results')
line.width = 400
line.height = 300
line.marks[0].marks[0].properties.enter.opacity = vincent.ValueRef(value=1)
line.marks[0].marks[0].properties.update = vincent.PropertySet()
line.marks[0].marks[0].properties.update.size = vincent.ValueRef(value=100)
line.marks[0].marks[0].properties.hover = vincent.PropertySet()
line.marks[0].marks[0].properties.hover.size = vincent.ValueRef(value=200)
line.marks[0].marks[0].properties.update.size = vincent.ValueRef(value=100)
line.marks[0].marks[0].properties.hover = vincent.PropertySet()
line.marks[0].marks[0].properties.hover.size = vincent.ValueRef(value=200)
line.scales['shape'] = vincent.Scale(
name='shape',
type='ordinal',
domain=vincent.DataRef(data='table', field='data.col'),
range=["square", "circle", "triangle-down", "triangle-up"])
line.marks[0].marks[0].properties.enter.shape = vincent.ValueRef(
scale="shape", field="data.col")
line.legends[0].shape = "shape"
return line
df = pd.read_csv('data/us_county_data_vincent.csv', na_values=[' '])
df['FIPS_Code'] = df['FIPS'].astype(str)
#Perform an inner join, pad NA's with data from nearest county
merged = pd.merge(df, county_df, on='FIPS', how='inner')
merged = merged.fillna(method='pad')
# <codecell>
geo_data = [{'name': 'counties',
'url': 'files/vincent_map_data/us_counties_intfips.topo.json',
'feature': 'us_counties.geo'}]
vis = vincent.Map(data=merged, geo_data=geo_data, scale=1100,
projection='albersUsa', data_bind='Employed_2011',
data_key='FIPS', map_key={'counties': 'properties.FIPS'})
vis.marks[0].properties.enter.stroke_opacity = vincent.ValueRef(value=0.5)
#Change our domain for an even inteager
vis.scales['color'].domain = [0, 189000]
vis.legend(title='Number Employed 2011')
vis.to_json('unemployed.json', html_out=True, html_path='unemployed_map.html')
# <codecell>
vis.display()
# <codecell>
import vincent as vince
from pandasql import sqldf
import matplotlib.pyplot as plt
import numpy as np
import json
import csv
freq_data = pd.read_csv('freq_data.csv', delimiter=',')
pysqldf = lambda q: sqldf(q, globals())
## use pandas dataframe to create Vincent frequency histogram vizualization to be passed to Vega later.
q = """SELECT * FROM freq_data ORDER BY frequency DESC LIMIT 20;"""
viz_data = pysqldf(q)
vis = vince.Bar(viz_data, columns=['frequency'], key_on='word', height=400)
vis.axes[0].properties = vince.AxisProperties(labels=vince.PropertySet(
angle=vince.ValueRef(value=45), align=vince.ValueRef(value='left')))
#vis.padding['bottom'] = 90
vis.axis_titles(y='Frequency (%)', x='Word')
vis.legend('20 Most Frequent Words in Tweets (%)')
vis.to_json('vega.json')
vis.colors(brew='RdPu')
words = viz_data['word']
frequency = viz_data['frequency']
##create matplotlib frequency histogram
ind = np.arange(20) # the x locations for the groups
width = 0.5
fig, ax = plt.subplots()
rects1 = ax.bar(ind, frequency, width, color='#98FB98')
ax.set_ylabel('(%) Frequency')
ax.set_xticks(ind + width)
def plotrwtraversal(G, expensiveedges=[], time=None, countfrogs=False):
data = []
index = []
for e in G.edges_iter():
key = edgetokey((e[0], e[1]))
sr = pd.Series(G.edge[e[0]][e[1]]['timeline'])
if not countfrogs:
sr[sr > 0] = 1
data.append(sr)
index.append(key)
if time:
data.append(pd.Series(time * [0]))
index.append('hack')
df = pd.DataFrame(data, index=index).T
if time:
del df['hack']
dfexp = df[expensiveedges].copy()
dfcheap = df.copy()
dfcheap.drop(expensiveedges, 1, inplace=True)
dfexpcopy = dfexp.copy()
dfexpcopy[dfexp > 0] = 1
cost = (dfexpcopy.sum(axis=1)).sum()
G.graph['cost'] = cost
if len(expensiveedges) > 0:
datacost = []
indexcost = []
datacost.append(dfexp.sum(axis=1))
indexcost.append('Expensive')
datacost.append(dfcheap.sum(axis=1))
indexcost.append('Cheap')
dfcost = pd.DataFrame(datacost, index=indexcost).T
finaldf = dfcost
else:
finaldf = df
showteleportations = (len(G.graph['teleportations']) > 0) and countfrogs
if showteleportations:
# Count teleportations
finaldf['Teleportation'] = pd.Series(G.graph['teleportations'])
try:
if countfrogs and len(G.graph['waiting']) > 0:
finaldf['Waiting'] = pd.Series(G.graph['waiting'])
except:
pass
line = vincent.StackedArea(finaldf)
if not countfrogs:
line.axis_titles(x='Rounds', y='# edges traversed')
else:
line.axis_titles(x='Rounds', y='# frogs')
line.legend(title='Edge')
line.width = 400
line.height = 300
if not countfrogs:
line.scales[1].domain = [0, G.size()]
line.marks[0].marks[0].properties.enter.opacity = vincent.ValueRef(
value=0.8)
if len(expensiveedges) > 0:
if showteleportations:
line.colors(range_=['#ff0000', '#50aa50', '#6060aa', '#eeeeee'])
else:
line.colors(range_=['#ff0000', '#50aa50', '#eeeeee'])
line.marks[0].marks[0].properties.update = vincent.PropertySet()
line.marks[0].marks[0].properties.update.size = vincent.ValueRef(value=100)
line.marks[0].marks[0].properties.hover = vincent.PropertySet()
line.marks[0].marks[0].properties.hover.size = vincent.ValueRef(value=200)
line.marks[0].marks[0].properties.update.opacity = vincent.ValueRef(
value=0.8)
line.marks[0].marks[0].properties.hover.opacity = vincent.ValueRef(value=1)
return line, finaldf
return res
def word_occurences(data):
#Define stopwords
punctuation = list(string.punctuation)
stop = stopwords.words('english') + stopwords.words('french')
stop += ['les']
stop += punctuation
stop += ['rt', 'via']
stop += list(string.ascii_letters)
stop += ['...','…',"'",'’']
count_all = collections.Counter()
count_all.update([word for tweet in tweets for word in tweet if word not in stop])
return count_all.most_common(25)
if __name__ == '__main__':
load_online_data()
tweets = load_and_tokenize()
top_occurences = word_occurences(tweets)
labels, freq = zip(*top_occurences)
data = {'data': freq, 'x': labels}
bar = vincent.Bar(data, iter_idx='x')
#rotate x axis labels
ax = vincent.AxisProperties(labels = vincent.PropertySet(angle=vincent.ValueRef(value=90)))
bar.axes[0].properties = ax
#Export visu to JSON file
bar.to_json('term_freq.json')