def main():
# creating object of TwitterClient Class
api = TwitterClient()
# calling function to get tweets
tweets = api.get_tweets(query = 'OnePlus', count = 200) # you can increase the count for more acurate result
# picking positive tweets from tweets
ptweets = [tweet for tweet in tweets if tweet['sentiment'] == 'positive']
# percentage of positive tweets
print("Positive tweets percentage: {} %".format(100*len(ptweets)/len(tweets)))
# picking negative tweets from tweets
ntweets = [tweet for tweet in tweets if tweet['sentiment'] == 'negative']
# percentage of negative tweets
print("Negative tweets percentage: {} %".format(100*len(ntweets)/len(tweets)))
# percentage of neutral tweets
nutweets = len(tweets) - len(ntweets) - len(ptweets)
print("Neutral tweets percentage: {} %".format(100*nutweets/len(tweets)))
ptweetper = 100*len(ptweets)/len(tweets)
ntweetper = 100*len(ntweets)/len(tweets)
nutweetper = 100*nutweets/len(tweets)
labels = ['Positive_tweets','Negative_tweets','Neutral_Tweets']
values = [ptweetper,ntweetper,nutweetper]
trace = go.Pie(labels=labels, values=values)
py.iplot([trace], filename='sentiment_analysis_OnePlus')
def main():
idata_train, idata_test, itargets_train, itargets_test = load_iris()
# Use my classifier on Iris
num_loops = 100
classifier = NNClassifier(4, [10, 3])
list1 = classifier.fit(idata_train, itargets_train, idata_test,
itargets_test, num_loops)
# Create trace 1
trace1 = go.Scatter(x=np.arange(num_loops),
y=np.asarray(list1),
mode='lines',
name='lines')
data_train, data_test, targets_train, targets_test = load_pima_indian_diabetes(
)
# Use my classifier on Pima Indian Diabetes
num_loops = 50
classifier = NNClassifier(8, [7, 2])
list2 = classifier.fit(data_train, targets_train, data_test, targets_test,
50)
# Create trace 2
trace1 = go.Scatter(x=np.arange(num_loops),
y=np.asarray(list2),
mode='lines',
name='lines')
data = [trace1, trace2]
py.iplot(data, filename='line-mode')
def precipitacao(self):
data = [
dict(type='scattergeo',
lon=[],
lat=[],
mode='markers',
marker=dict(
size=8,
opacity=0.8,
reversescale=True,
autocolorscale=False,
line=dict(width=1, color='rgba(102, 102, 102)'),
),
stream=stream_id,
name="Plane")
]
layout = dict(
title='Busy Airplane Streaming',
colorbar=False,
geo=dict(scope='usa',
projection=dict(type='albers usa'),
showland=True,
landcolor="rgb(250, 250, 250)",
subunitcolor="rgb(217, 217, 217)",
countrycolor="rgb(217, 217, 217)",
countrywidth=0.5,
subunitwidth=0.5),
)
fig = dict(data=data, layout=layout)
py.iplot(fig,
validate=False,
filename='geo-streaming2',
auto_open=False,
fileopt='extend')
data = TwitterData_Wordlist(data)
data.build_wordlist()
words = pd.read_csv(r"C:\Users\Caroline\Documents\twitractors\ml-twitter-sentiment-analysis-develop\data\wordlist.csv")
x_words = list(words.loc[0:10,"word"])
x_words.reverse()
y_occ = list(words.loc[0:10,"occurrences"])
y_occ.reverse()
dist = [
graph_objs.Bar(
x=y_occ,
y=x_words,
orientation="h"
)]
plotly.iplot({"data":dist, "layout":graph_objs.Layout(title="Top words in built wordlist")})
class TwitterData_BagOfWords(TwitterData_Wordlist):
def __init__(self, previous):
self.processed_data = previous.processed_data
self.wordlist = previous.wordlist
def build_data_model(self):
label_column = []
if not self.is_testing:
label_column = ["label"]
columns = label_column + list(
map(lambda w: w + "_bow", self.wordlist))
labels = []
import plotly as py
py.tools.set_credentials_file(username='******', api_key='lr1c37zw81')
import plotly.graph_objs as go
import datetime
def to_unix_time(dt):
epoch = datetime.datetime.utcfromtimestamp(0)
return (dt - epoch).total_seconds() * 1000
x = [
datetime.datetime(year=2013, month=10, day=4),
datetime.datetime(year=2013, month=11, day=5),
datetime.datetime(year=2013, month=12, day=6)
]
data = [go.Scatter(x=x, y=[1, 3, 6])]
layout = go.Layout(xaxis=dict(range=[
to_unix_time(datetime.datetime(2013, 10, 17)),
to_unix_time(datetime.datetime(2013, 11, 20))
]))
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)
if len(quotes) == 0:
print "Couldn't connect to yahoo trading database"
else:
dates = [q[0] for q in quotes]
y = [q[1] for q in quotes]
for date in dates:
x.append(datetime.fromordinal(int(date))\
.strftime('%Y-%m-%d')) # Plotly timestamp format
ma = moving_average(y, 10)
# vvv clip first and last points of convolution
mov_avg = go.Scatter( x=x[5:-4], y=ma[5:-4], \
line=dict(width=2,color='red',opacity=0.5), name='Moving average' )
data = [xy_data, mov_avg]
py.iplot(data, filename='apple stock moving average')
first_plot_url = py.plot(data, filename='apple stock moving average', auto_open=False,)
print first_plot_url
tickers = ['AAPL', 'GE', 'IBM', 'KO', 'MSFT', 'PEP']
prices = []
for ticker in tickers:
quotes = quotes_historical_yahoo(ticker, date1, date2)
prices.append( [q[1] for q in quotes] )
df = pd.DataFrame( prices ).transpose()
df.columns = tickers
df.head()
fig = plotly_tools.get_subplots(rows=6, columns=6, print_grid=True, horizontal_spacing= 0.05, vertical_spacing= 0.05)
br02 = go.Scatter(y=origBR['Attention'],
x=origBR['Time:512Hz'],
mode='lines',
name='Attention')
br03 = go.Scatter(y=origBR['Meditation'],
x=origBR['Time:512Hz'],
mode='lines',
name='Meditation')
layout_br0 = go.Layout(title='Plot of Original Big Rigs CSV Data',
plot_bgcolor='rgb(230, 230, 230)')
fig_br0 = go.Figure(data=[br01, br02, br03], layout=layout_br0)
# Plot data in the notebook
py.iplot(fig_br0, filename='plot-from-orig-br0-csv')
# #### Need for Speed: Hot Pursuit 2 (Average Rated Game)
# In[6]:
hp01 = go.Scatter(
y=origHP['Electrode'],
x=origHP['Time:512Hz'], # Data
mode='lines',
name='Electrode' # Additional options
)
hp02 = go.Scatter(y=origHP['Attention'],
x=origHP['Time:512Hz'],
mode='lines',
name='Attention')
trace2 = go.Sunburst(ids=df2.ids,
labels=df2.labels,
parents=df2.parents,
domain=dict(column=1),
maxdepth=2)
layout = go.Layout(grid=go.layout.Grid(columns=2, rows=1),
margin=go.layout.Margin(t=0, l=0, r=0, b=0),
sunburstcolorway=[
"#636efa", "#EF553B", "#00cc96", "#ab63fa", "#19d3f3",
"#e763fa", "#FECB52", "#FFA15A", "#FF6692", "#B6E880"
],
extendsunburstcolors=True)
data = [trace1, trace2]
fig = go.Figure(data, layout)
plotly.iplot(fig, filename='large_number_of_slices')
@app.route('/sui_d3sunburst', methods=['GET', 'POST'])
def sui_d3sunburst():
return render_template('sui-d3sunburst.html')
if __name__ == '__main__':
app.secret_key = 'secret123'
app.run(debug=True)
from IPython.display import HTML
x = []
y = []
ma = []
def moving_average(interval, window_size):
window = np.ones(int(window_size))/float(window_size)
return np.convolve(interval, window, 'same')
date1 = dt_date( 2014, 1, 1 )
date2 = dt_date( 2014, 12, 12 )
quotes = quotes_historical_yahoo('AAPL', date1, date2)
if len(quotes) == 0:
print "Couldn't connect to yahoo trading database"
else:
dates = [q[0] for q in quotes]
y = [q[1] for q in quotes]
for date in dates:
x.append(datetime.fromordinal(int(date))\
.strftime('%Y-%m-%d')) # Plotly timestamp format
ma = moving_average(y, 10)
xy_data = go.Scatter( x=x, y=y, mode='markers', marker=dict(size=4), name='AAPL' )
# vvv clip first and last points of convolution
mov_avg = go.Scatter( x=x[5:-4], y=ma[5:-4], \
line=dict(width=2,color='red',opacity=0.5), name='Moving average' )
data = [xy_data, mov_avg]
py.iplot(data, filename='apple stock moving average')
def create_total_line_graph(data_frame):
colors = [
'#33CFA5', 'orange', '#F06A6A', 'blue', 'violet', 'yellowgreen',
'darkgrey', 'goldenrod'
]
products = data_frame['product'].unique().tolist()
month_year_list = data_frame['month-year'].unique().tolist()
month_year_list = sorted(month_year_list)
products = sorted(products)
#print(products)
data_list = []
for i in range(0, len(products)):
x_list = []
y_list = []
temp_frame = data_frame[data_frame['product'] == products[i]]
for key in month_year_list:
temp_month_frame = temp_frame[temp_frame['month-year'] == key]
x_list.append(key)
y_list.append(get_total_sales(temp_month_frame))
#print(x_list, y_list)
#print(colors[i])
temp_scatter = go.Scatter(x=x_list,
y=y_list,
name=products[i],
line=dict(color=colors[i]))
data_list.append(temp_scatter)
updatemenus = list([
dict(
type="buttons",
active=-1,
buttons=list([
dict(label='Brown Boots',
method='update',
args=[{
'visible': [
True, False, False, False, False, False, False,
False
]
}, {
'title': 'Brown Boots Sales over Time ($)',
'annotations': []
}]),
dict(label='Button-Down Shirt',
method='update',
args=[{
'visible': [
False, True, False, False, False, False, False,
False
]
}, {
'title': 'Button-Down Shirt Sales over Time ($)',
'annotations': []
}]),
dict(label='Khaki Pants',
method='update',
args=[{
'visible': [
False, False, True, False, False, False, False,
False
]
}, {
'title': 'Khaki Pants Sales over Time ($)',
'annotations': []
}]),
dict(label='Sticker Pack',
method='update',
args=[{
'visible': [
False, False, False, True, False, False, False,
False
]
}, {
'title': 'Sticker Pack Sales over Time ($)',
'annotations': []
}]),
dict(label='Super Soft Hoodie',
method='update',
args=[{
'visible': [
False, False, False, False, True, False, False,
False
]
}, {
'title': 'Super Soft Hoodie Sales over Time ($)',
'annotations': []
}]),
dict(label='Super Soft Sweater',
method='update',
args=[{
'visible': [
False, False, False, False, False, True, False,
False
]
}, {
'title': 'Super Soft Sweater Sales over Time ($)',
'annotations': []
}]),
dict(label='Vintage Logo Tee',
method='update',
args=[{
'visible': [
False, False, False, False, False, False, True,
False
]
}, {
'title': 'Vintage Logo Tee Sales over Time ($)',
'annotations': []
}]),
dict(label='Winter Hat',
method='update',
args=[{
'visible': [
False, False, False, False, False, False, False,
True
]
}, {
'title': 'Winter Hat Sales over Time ($)',
'annotations': []
}]),
dict(label='All',
method='update',
args=[{
'visible':
[True, True, True, True, True, True, True, True]
}, {
'title': 'All Sales over Time ($)',
'annotations': []
}])
]),
)
])
layout = dict(title='Total Sales vs Month Per Product',
showlegend=False,
xaxis=dict(title='Time (Months)'),
yaxis=dict(title='Sales ($)'),
updatemenus=updatemenus)
fig = dict(data=data_list, layout=layout)
py.iplot(fig, filename='sales-vs-month-int')
x = subset.loc[subset['kmeans_0']==n, DADcolsscaled[0]]
y = subset.loc[subset['kmeans_0']==n, DADcolsscaled[1]]
# Calculate the point density
xy = np.vstack([x,y])
z1 = gaussian_kde(xy)(xy)
cb1 = ax.scatter(x, y, c=z1, cmap=cmaps[n], s=50, edgecolor=None,edgecolors=None,alpha=1)
plt.colorbar(cb1, ax=ax)
ax.set_xlim([-1, 2])
ax.set_ylim([-1, 2])
ax.set_xlabel(DADcolsscaled[0])
ax.set_ylabel(DADcolsscaled[1])
ax.set_axis_bgcolor('white')
ax.grid(b=True, which='both', color="gray",linestyle='-',alpha=.1)
plt.tight_layout(pad=0.8, w_pad=0.8, h_pad=1.0)
fig = plt.gcf()
py.plot_mpl(fig, filename="mpl-colormaps-simple")
plt.show()
layout = dict(title = 'Styled Scatter',
yaxis = dict(zeroline = False),
xaxis = dict(zeroline = False)
)
fig = dict(data=data, layout=layout)
py.iplot(fig, filename='styled-scatter', colorscale = cmaps)
y=df2['AvgPoints'],
name='Average Points per Game'
)
trace2 = go.Bar( #The second column - No Dependent Status
x=df2['Team'],
y=df2['AvgAssist'],
name='Average Assists per Game'
)
data4 = [trace1, trace2] #read four columns into one data
layout4 = go.Layout( #starting to plot a grouped bar chart
title='Team performance',
barmode='group'
)
fig = go.Figure(data=data4, layout=layout4)
py.iplot(fig, filename='grouped-bar')
# In[14]:
"""look at shooting performance by team"""
trace1 = go.Bar( #The first column - Level III Salary
x=df2['Team'],
y=df2['FGPct'],
name='Average Field Goal Percentage'
)
trace2 = go.Bar( #The second column - No Dependent Status
x=df2['Team'],
y=df2['ThreePct'],
name='Average Three Pointer Percentage'
#Simples
chuvas_smm.plot(x=chuvas_smm.index, y=['Total', 'Maxima'])
#Boxplot (Gráficos interativos via Plotly)
total1= go.Box(
y=chuvas_smm["Total"]
)
maxima1 = go.Box(
y=chuvas_smm["Maxima"]
)
smm_box_mt= [total1, maxima1]
py.offline.plot(smm_box_mt, filename="chuvas_smm_box.html")
#Visualização de Série Temporal (GI)
#Maxima Mensal
chuvas_dg_max= [go.Scatter(x=chuvas_smm.index, y=chuvas_smm['Maxima'] )]
py.iplot(chuvas_dg_max, filename='chuvas_dg_max.html')
#Dias de chuva
chuvas_smm_dias= [go.Scatter(x=chuvas_smm.index, y=chuvas_smm['NumDiasDeChuva'] )]
py.offline.plot(chuvas_smm_dias, filename='chuvas_smm_dias.html')
#Gantt (GI)
#Delmiro Gouveia
#Simples
chuvas_dg.plot(x='Data', y=['Total', 'Maxima'])
#Boxplot (Graficos interativos via Plotly)
total2= go.Box(
y=chuvas_dg["Total"]
)
maxima2 = go.Box(
y=chuvas_dg["Maxima"]
separator = ','
for item in data.cuisines:
item_list = item.split(',')
new_list = []
for it in item_list:
str_content = it.strip()
new_list.append(str_content)
main_list.append(separator.join(sorted(new_list)))
data['new_cuisines'] = main_list
data['new_cuisines'][0]
# Visualization
location_count = data.groupby(['place']).size().reset_index(name="count")
location_count = location_count.sort_values('count', ascending=True)
location_count.head()
inputdata = [go.Bar(x=location_count['place'], y=location_count['count'])]
py.iplot(inputdata, filename='basic-bar')
plt.show()
rate_group_count = data.groupby(['rate']).size().reset_index(name="count")
rate_group_count = rate_group_count.sort_values('count', ascending=True)
rate_group_count.head()
inputdata = [go.Bar(x=rate_group_count['rate'], y=rate_group_count['count'])]
py.iplot(inputdata, filename='basic-bar')
plt.show()
name_group_count = data.groupby(['name']).size().reset_index(name="count")
name_group_count = name_group_count.sort_values('count', ascending=False)
#name_group_count.head()
top20 = name_group_count[0:20]
top20
inputdata = [go.Bar(x=top20['name'], y=top20['count'])]
py.iplot(inputdata, filename='basic-bar')
plt.show()
window = np.ones(int(window_size))/float(window_size)
return np.convolve(interval, window, 'same')
date1 = dt_date( 2014, 1, 1 )
date2 = dt_date( 2014, 12, 12 )
quotes = quotes_historical_yahoo('AAPL', date1, date2)
if len(quotes) == 0:
print "Couldn't connect to yahoo trading database"
else:
dates = [q[0] for q in quotes]
y = [q[1] for q in quotes]
for date in dates:
x.append(datetime.fromordinal(int(date))\
.strftime('%Y-%m-%d')) # Plotly timestamp format
ma = moving_average(y, 10)
#Now graph the data with Plotly. See here for Plotly's line plot
#syntax and here for getting started with the Plotly Python client.
xy_data = Scatter( x=x, y=y, mode='markers', marker=Marker(size=4), name='AAPL' )
# vvv clip first and last points of convolution
mov_avg = Scatter( x=x[5:-4], y=ma[5:-4], \
line=Line(width=2,color='red',opacity=0.5), name='Moving average' )
data = Data([xy_data, mov_avg])
py.iplot(data, filename='apple stock moving average')
#Save the plot URL - we'll use it when generating the report later.
first_plot_url = py.plot(data, filename='apple stock moving average', auto_open=False,)
print first_plot_url
print(str(count) + '. ' + item + ' ' + '${0:,.2f}'.format(temp_float))
count = count + 1
if count > 3:
break
#from https://github.com/madelinenlee/OPIM-243-chart-exercise
x = []
y = []
for item in product_subtotals:
y.append(item)
x.append('$' + str(product_subtotals[item]))
x = list(reversed(x))
data = [go.Bar(x=x, y=y, orientation='h')]
margin = go.Margin(l=200, r=50)
layout = go.Layout(title='Top Selling Products (' + month + ' ' + year + ')',
xaxis=dict(title='USD ($)'),
yaxis=dict(title='Product'),
margin=margin)
figure = go.Figure(data=data, layout=layout)
py.iplot(figure, filename='horizontal-bar.html')
print(
'see your top selling products for this month at https://plot.ly/~madelinelee/75'
)
#https://plot.ly/~madelinelee/75