def plotly_map():
mapbox_access_token = 'pk.eyJ1Ijoic3VodHdpbnMiLCJhIjoi' +\
'Y2pnNGJvbXRhMGpoNDJwcWRva3JieWgwcCJ9' +\
'.cmsuwG65XkGUh2pv07nIVg'
data = Data([
Scattermapbox(
lat=['37.7765', '37.791377'],
lon=['-122.4506', '-122.392609'],
mode='markers',
marker=Marker(size=15),
text=["University of San Francisco, Main Campus",
"University of San Francisco, Downtown Campus"])])
layout = Layout(
autosize=True,
hovermode='closest',
mapbox=dict(
accesstoken=mapbox_access_token,
bearing=0,
center=dict(
lat=37.773972,
lon=-122.431297
),
pitch=0,
zoom=11
),
)
fig = dict(data=data, layout=layout)
output = plotly.offline.plot(fig, include_plotlyjs=False,
output_type='div')
activities_grouped_df = activities_df.groupby(['date'], as_index=False)['miles'].sum()
activities_grouped_df['dow'] = activities_grouped_df.date.apply(lambda x: x.weekday())
activities_grouped_df['week_start'] = activities_grouped_df.date.apply(lambda x: x - timedelta(days=x.weekday()))
miles_per_week = activities_grouped_df.groupby(['week_start'], as_index=False).miles.sum()
by_week_df = pd.DataFrame(activities_grouped_df.week_start.unique(), columns=['week_start'])
for i in range(7):
by_week_df['{}'.format(i)] = i
for i in range(7):
by_week_df = pd.merge(by_week_df, activities_grouped_df, left_on=['week_start', '{}'.format(i)],
right_on=['week_start', 'dow'], how='left', suffixes=('', '_{}'.format(i)))
by_week_df = by_week_df[['week_start', 'miles', 'miles_1', 'miles_2', 'miles_3', 'miles_4', 'miles_5', 'miles_6']]
by_week_df.columns = ['week_start', 'miles_0', 'miles_1', 'miles_2', 'miles_3', 'miles_4', 'miles_5', 'miles_6']
by_week_df['year'] = by_week_df['week_start'].apply(lambda x: x.year)
by_week_df.fillna(0, inplace=True)
by_week_df = pd.merge(by_week_df, miles_per_week, how='left', on='week_start')
days_dict = {0: 'Monday', 1: 'Tuesday', 2: 'Wednesday', 3: 'Thursday', 4: 'Friday', 5: 'Saturday', 6: 'Sunday'}
dimensions = list()
for i in range(7):
dimensions.append(
dict(range=[0, 20],
constraintrange=[0, 20],
label='{}'.format(days_dict[i]), values=by_week_df['miles_{}'.format(i)]))
data = [
go.Parcoords(
line=dict(color=by_week_df['miles'],
colorscale='Hot',
showscale=True,
reversescale=True),
opacity=0.5,
dimensions=dimensions, hoverinfo='text')
]
layout = go.Layout(
plot_bgcolor='#E5E5E5',
paper_bgcolor='#E5E5E5',
title='Miles per week broken down by day'
)
fig = go.Figure(data=data, layout=layout)
output2 = plotly.offline.plot(fig, include_plotlyjs=False,
output_type='div')
activities_df['week_start'] = activities_df.date.apply(lambda x: x - timedelta(days=x.weekday()))
activities_grouped_df_2 = activities_df.groupby(['workout_type', 'week_start'], as_index=False)['miles'].sum()
by_week_activity_df = pd.DataFrame(activities_grouped_df_2.week_start.unique(), columns=['week_start'])
for i in activities_df.workout_type.unique():
by_week_activity_df['{}'.format(i)] = i
for i in range(4):
by_week_activity_df = pd.merge(by_week_activity_df, activities_grouped_df_2,
left_on=['week_start', '{}'.format(activities_df.workout_type.unique()[i])],
right_on=['week_start', 'workout_type'], how='left',
suffixes=('', '_{}'.format(activities_df.workout_type.unique()[i])))
by_week_activity_df = by_week_activity_df[['week_start', 'miles', 'miles_Workout', 'miles_Long Run', 'miles_Race']]
by_week_activity_df.columns = ['week_start', 'miles_Run', 'miles_Workout', 'miles_Long Run', 'miles_Race']
by_week_activity_df.fillna(0, inplace=True)
by_week_activity_df['miles_Run'] = np.array(by_week_activity_df['miles_Run']) + np.array(
by_week_activity_df['miles_Long Run'])
by_week_activity_df['miles_Run'] = np.array(by_week_activity_df['miles_Run']) + np.array(
by_week_activity_df['miles_Long Run'])
data = []
custom_colours = ['blue', 'orange', 'red']
j = 0
for i in ['Run', 'Workout', 'Race']:
data.append(go.Bar(
x=by_week_activity_df['week_start'],
y=by_week_activity_df['miles_{}'.format(i)],
marker=dict(color=custom_colours[j]),
name=i))
j += 1
layout = dict(
barmode='stack',
hovermode='closest',
title='Miles per week',
xaxis=dict(
rangeselector=dict(
buttons=list([
dict(count=1,
label='1m',
step='month',
stepmode='backward'),
dict(count=6,
label='6m',
step='month',
stepmode='backward'),
dict(count=1,
label='YTD',
step='year',
stepmode='todate'),
dict(count=1,
label='1y',
step='year',
stepmode='backward'),
dict(step='all')
])
),
rangeslider=dict(),
type='date'
)
)
fig = go.Figure(data=data, layout=layout)
output3 = plotly.offline.plot(fig, include_plotlyjs=False,
output_type='div')
return(output,output2,output3)
# In[15]:
dates_borough['COUNT'] = 1
# In[16]:
date_borough_sum = dates_borough.groupby(['borough', "date"]).sum()
date_borough_sum.head()
# In[17]:
data = []
for g, df in date_borough_sum.reset_index().groupby('borough'):
data.append(Scatter(x= df.date, y=df.COUNT,name=g))
layout = Layout(xaxis=XAxis(title="Date"), yaxis=YAxis(title="Accident Count"))
# In[18]:
py.iplot(Figure(data=Data(data), layout=layout), filename='nypd_crashes/over_time')
# Luckily for us, while this graph is a bit of a mess, we can still zoom in on specific times and ranges. This makes plotly perfect for exploring datasets. You can create a high level visual of the data then zoom into a more detailed level.
#
# See below where using the above graph I could zoom in on a particular point and anontate it for future investigation.
# In[19]:
tls.embed("https://plot.ly/~bill_chambers/274")
def fig2():
# (!) Set 'size' values to be proportional to rendered area,
# instead of diameter. This makes the range of bubble sizes smaller
sizemode = 'area'
# (!) Set a reference for 'size' values (i.e. a population-to-pixel scaling).
# Here the max bubble area will be on the order of 100 pixels
sizeref = df['Population'].max() / 1e2 ** 2
colors = {
'Asia': "rgb(255,65,54)",
'Europe': "rgb(133,20,75)",
'Africa': "rgb(0,116,217)",
'North America': "rgb(255,133,27)",
'South America': "rgb(23,190,207)",
'Antarctica': "rgb(61,153,112)",
'Oceania': "rgb(255,220,0)",
}
# Define a hover-text generating function (returns a list of strings)
def make_text(X):
return 'Country: %s\
<br>Life Expectancy: %s years\
<br>Population: %s million' \
% (X['Name'], X['LifeExpectancy'], X['Population'] / 1e6)
# Define a trace-generating function (returns a Scatter object)
def make_trace(X, continent, sizes, color):
return Scatter(
x=X['GNP'], # GDP on the x-xaxis
y=X['LifeExpectancy'], # life Exp on th y-axis
name=continent, # label continent names on hover
mode='markers', # (!) point markers only on this plot
text=X.apply(make_text, axis=1).tolist(),
marker=Marker(
color=color, # marker color
size=sizes, # (!) marker sizes (sizes is a list)
sizeref=sizeref, # link sizeref
sizemode=sizemode, # link sizemode
opacity=0.6, # (!) partly transparent markers
line=Line(width=3, color="white") # marker borders
)
)
# Initialize data object
data = Data()
# Group data frame by continent sub-dataframe (named X),
# make one trace object per continent and append to data object
for continent, X in df.groupby('Continent'):
sizes = X['Population'] # get population array
color = colors[continent] # get bubble color
data.append(
make_trace(X, continent, sizes, color) # append trace to data object
)
# Set plot and axis titles
title = "Life expectancy vs GNP from MySQL world database (bubble chart)"
x_title = "Gross National Product"
y_title = "Life Expectancy [in years]"
# Define a dictionary of axis style options
axis_style = dict(
type='log',
zeroline=False, # remove thick zero line
gridcolor='#FFFFFF', # white grid lines
ticks='outside', # draw ticks outside axes
ticklen=8, # tick length
tickwidth=1.5 # and width
)
# Make layout object
layout = Layout(
title=title, # set plot title
plot_bgcolor='#EFECEA', # set plot color to grey
hovermode="closest",
xaxis=XAxis(
axis_style, # add axis style dictionary
title=x_title, # x-axis title
range=[2.0, 7.2], # log of min and max x limits
),
yaxis=YAxis(
axis_style, # add axis style dictionary
title=y_title, # y-axis title
)
)
# Make Figure object
fig = Figure(data=data, layout=layout)
# (@) Send to Plotly and show in notebook
py.iplot(fig, filename='s3_life-gdp')
def fig2():
# (!) Set 'size' values to be proportional to rendered area,
# instead of diameter. This makes the range of bubble sizes smaller
sizemode = 'area'
# (!) Set a reference for 'size' values (i.e. a population-to-pixel scaling).
# Here the max bubble area will be on the order of 100 pixels
sizeref = df['Population'].max() / 1e2 ** 2
colors = {
'Asia': "rgb(255,65,54)",
'Europe': "rgb(133,20,75)",
'Africa': "rgb(0,116,217)",
'North America': "rgb(255,133,27)",
'South America': "rgb(23,190,207)",
'Antarctica': "rgb(61,153,112)",
'Oceania': "rgb(255,220,0)",
}
# Define a hover-text generating function (returns a list of strings)
def make_text(X):
return 'Country: %s\
<br>Life Expectancy: %s years\
<br>Population: %s million' \
% (X['Name'], X['LifeExpectancy'], X['Population'] / 1e6)
# Define a trace-generating function (returns a Scatter object)
def make_trace(X, continent, sizes, color):
return Scatter(
x=X['GNP'], # GDP on the x-xaxis
y=X['LifeExpectancy'], # life Exp on th y-axis
name=continent, # label continent names on hover
mode='markers', # (!) point markers only on this plot
text=X.apply(make_text, axis=1).tolist(),
marker=Marker(
color=color, # marker color
size=sizes, # (!) marker sizes (sizes is a list)
sizeref=sizeref, # link sizeref
sizemode=sizemode, # link sizemode
opacity=0.6, # (!) partly transparent markers
line=Line(width=3, color="white") # marker borders
)
)
# Initialize data object
data = Data()
# Group data frame by continent sub-dataframe (named X),
# make one trace object per continent and append to data object
for continent, X in df.groupby('Continent'):
sizes = X['Population'] # get population array
color = colors[continent] # get bubble color
data.append(
make_trace(X, continent, sizes, color) # append trace to data object
)
# Set plot and axis titles
title = "Life expectancy vs GNP from MySQL world database (bubble chart)"
x_title = "Gross National Product"
y_title = "Life Expectancy [in years]"
# Define a dictionary of axis style options
axis_style = dict(
type='log',
zeroline=False, # remove thick zero line
gridcolor='#FFFFFF', # white grid lines
ticks='outside', # draw ticks outside axes
ticklen=8, # tick length
tickwidth=1.5 # and width
)
# Make layout object
layout = Layout(
title=title, # set plot title
plot_bgcolor='#EFECEA', # set plot color to grey
hovermode="closest",
xaxis=XAxis(
axis_style, # add axis style dictionary
title=x_title, # x-axis title
range=[2.0, 7.2], # log of min and max x limits
),
yaxis=YAxis(
axis_style, # add axis style dictionary
title=y_title, # y-axis title
)
)
# Make Figure object
fig = Figure(data=data, layout=layout)
# (@) Send to Plotly and show in notebook
py.iplot(fig, filename='s3_life-gdp')
def test_validate_error():
data = Data()
data.append({'not-a-key': 'anything'})
data.validate()