def draw():
data_sources = ['2010YumaAZ.csv', '2010SantaBarbaraCA.csv', '2010SitkaAK.csv']
data_source = np.random.choice(data_sources)
csv_path = find_raw_csv_path(data_source)
df = pd.read_csv(csv_path)
colorscales = [
'Greys', 'YlGnBu', 'Greens', 'YlOrRd', 'Bluered', 'RdBu',
'Reds', 'Blues', 'Picnic', 'Rainbow', 'Portland', 'Jet',
'Hot', 'Blackbody', 'Earth', 'Electric', 'Viridis', 'Cividis'
]
colorscale = np.random.choice(colorscales)
data = [go.Heatmap(
x=df['DAY'],
y=df['LST_TIME'],
z=df['T_HR_AVG'],
colorscale=colorscale
)]
layout = go.Layout(
title=f"{' '.join((data_source.rsplit('.', 1)[0][:4], data_source.rsplit('.', 1)[0][4:-2], data_source.rsplit('.', 1)[0][-2:]))} Temperature ({colorscale})",
yaxis={'title': 'TIME'},
xaxis={'title': 'WEEKDAY'},
hovermode="x"
)
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
csv_path = find_raw_csv_path('iris.csv')
df = pd.read_csv(csv_path)
dim = 'petal_length'
classes = df['class'].unique()
hist_data = [df[df['class'] == c][dim] for c in classes]
group_labels = classes
bins = [1 for c in classes]
fig = ff.create_distplot(
hist_data,
group_labels=group_labels,
bin_size=bins,
curve_type='kde', # 'kde' or 'normal'
colors=None,
rug_text=None,
histnorm='probability density', # 'probability density' or 'probability'
show_hist=True,
show_curve=True,
show_rug=True)
fig.layout.title = dim.title()
return fig
def draw():
csv_path = find_raw_csv_path('abalone.csv')
df = pd.read_csv(csv_path)
samples = {
'A': np.random.choice(df['rings'], 30, replace=False),
'B': np.random.choice(df['rings'], 20, replace=False)
}
boxpoints = request_arg('boxpoints', 'all', str, lambda x: x in
('all', 'outliers'))
jitter = request_arg('jitter', 0.5, float, lambda x: 0 <= x <= 1)
pointpos = request_arg('pointpos', -2, float, lambda x: -2 <= x <= 2)
data = [
go.Box(y=samples[sample],
name=sample,
boxpoints=boxpoints,
jitter=jitter,
pointpos=pointpos) for sample in samples
]
layout = go.Layout(title="Sample of abalone rings values",
yaxis={'title': 'Rings'},
hovermode="x")
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
csv_path = find_raw_csv_path('abalone.csv')
# sex,length,diameter,height,whole_weight,shucked_weight,viscera_weight,shell_weight,rings
df = pd.read_csv(csv_path)
dim = 'length'
x_series = df[dim]
x_min, x_max = x_series.min(), x_series.max()
size = request_arg('size', 0.02, int, lambda x: x in range(int(x_max + 1)))
data = [
go.Histogram(
x=x_series,
xbins=dict(start=min(0, x_min), end=max(1, x_max), size=size),
)
]
layout = go.Layout(title="abalone Histogram",
yaxis={'title': dim},
xaxis={'title': 'bins'},
hovermode="x")
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
csv_path = find_raw_csv_path('mpg.csv')
df = pd.read_csv(csv_path)
# df = df[df.horsepower == '?'] # Bad Data Points Exists in Data Set
max_bubble_size = 25
min_value = df['weight'].min()
max_value = df['weight'].max()
bubble_size = ((df['weight'] - min_value) /
(max_value - min_value + 1)) * max_bubble_size
data = [
go.Scatter(x=df['horsepower'],
y=df['mpg'],
text=df['name'],
mode="markers",
marker=dict(size=bubble_size,
color=df['cylinders'],
colorscale='Jet',
showscale=True))
]
layout = go.Layout(title="MPG Bubble Chart",
xaxis={'title': 'horsepower'},
yaxis={'title': 'mpg'},
hovermode="closest")
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
# create a DataFrame from the .csv file:
csv_path = find_raw_csv_path('mpg.csv')
df = pd.read_csv(csv_path)
max_bubble_size = 30
bubble_size_dimension = 'horsepower'
df[bubble_size_dimension] = pd.to_numeric(
df[bubble_size_dimension], errors='coerce') # Convert to numbers
min_value = df[bubble_size_dimension].min()
max_value = df[bubble_size_dimension].max()
df[bubble_size_dimension] = df[bubble_size_dimension].fillna(
min_value
) # Fill All NaN with min value (Not Zero, otherwise the min size will be too small)
bubble_size = ((df[bubble_size_dimension] - min_value) /
(max_value - min_value + 1)) * max_bubble_size
x_dimension = 'displacement'
y_dimension = 'acceleration'
color_dimension = 'model_year'
text_dimension = 'name'
# create traces using a list comprehension:
data = [
go.Scatter(x=df[x_dimension],
y=df[y_dimension],
text=df[text_dimension].str.title(),
name="mpg data",
mode="markers",
marker=dict(size=bubble_size,
color=df[color_dimension],
showscale=True))
]
# create a layout, remember to set the barmode here
layout = go.Layout(
title=f"MPG {x_dimension.title()} & {y_dimension.title()}",
xaxis={'title': x_dimension},
yaxis={'title': y_dimension},
hovermode="closest")
# create a fig from data & layout, and plot the fig.
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
csv_path = find_raw_csv_path('2018WinterOlympics.csv')
df = pd.read_csv(csv_path)
trace1 = go.Bar(x=df['NOC'], y=df['Gold'], name='Gold', marker={'color': '#FFFF00'})
trace2 = go.Bar(x=df['NOC'], y=df['Silver'], name='Silver', marker={'color': '#A0A0A0'})
trace3 = go.Bar(x=df['NOC'], y=df['Bronze'], name='Bronze', marker={'color': '#FF8000'})
data = [trace1, trace2, trace3]
barmode = request_arg('barmode', 'group', str, lambda x: x in ('group', 'stack', 'relative'))
layout = go.Layout(title="Bar Chart 2018 Winter Olympics",
yaxis={'title': 'Number of Medals'},
barmode=barmode)
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
fpath = find_raw_csv_path('nst-est2017-alldata.csv')
df = pd.read_csv(fpath)
df2 = df.loc[df['DIVISION'] == '1', :]
df2.set_index('NAME', inplace=True)
df2 = df2.loc[:, [col for col in df2.columns if col.startswith('POP')]]
data = [
go.Scatter(x=[col[-4:] for col in df2.columns],
y=df2.loc[name, :],
mode="lines+markers",
name=name) for name in df2.index
]
layout = go.Layout(title="Line Chart Example using Pandas")
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
# Create a pandas DataFrame from 2010YumaAZ.csv
csv_path = find_raw_csv_path('2010YumaAZ.csv')
df = pd.read_csv(csv_path)
# Use a for loop (or list comprehension to create traces for the data list)
data = [
go.Scatter(x=df.loc[df['DAY'] == weekday, 'LST_TIME'],
y=df.loc[df['DAY'] == weekday, 'T_HR_AVG'],
mode="lines+markers",
name=weekday) for weekday in df['DAY'].unique()
]
# Define the layout
layout = go.Layout(
title="Daily temperature from June 1-7, 2010 in Yuma, Arizona")
# Create a fig from data and layout, and plot the fig
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
# create a DataFrame from the .csv file:
csv_path = find_raw_csv_path('mocksurvey.csv')
df = pd.read_csv(csv_path, index_col=0)
# df.set_index(df.columns[0], inplace=True)
# create traces using a list comprehension:
series = request_arg('series', 'q', str, lambda x: x in ('q', 'r'))
ori = request_arg('orientation', 'v', str, lambda x: x in ('v', 'h'))
if series == 'q':
data = [
go.Bar(x=df.columns if ori == 'v' else df.loc[idx, :],
y=df.loc[idx, :] if ori == 'v' else df.columns,
name=idx,
orientation=ori) for idx in df.index
]
else:
data = [
go.Bar(x=df.index if ori == 'v' else df.loc[:, col],
y=df.loc[:, col] if ori == 'v' else df.index,
name=col,
orientation=ori) for col in df.columns
]
# create a layout, remember to set the barmode here
barmode = request_arg('barmode', 'group', str, lambda x: x in
('group', 'stack', 'relative'))
layout = go.Layout(
title="Mocksurvey Result",
yaxis={'title': 'Response Score'} if ori == 'v' else None,
xaxis={'title': 'Response Score'} if ori == 'h' else None,
barmode=barmode)
# create a fig from data & layout, and plot the fig.
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
csv_path = find_raw_csv_path('flights.csv')
df = pd.read_csv(csv_path)
z_series = df['passengers']
round_by = 5
data = [
go.Heatmap(y=df['month'],
x=df['year'],
z=z_series,
name='passengers',
colorscale='Portland',
zmin=(int(z_series.min() / round_by) + 1) * round_by,
zmax=(int(z_series.max() / round_by) + 1) * round_by)
]
layout = go.Layout(title="Passengers by flight Year & Month",
yaxis={'title': 'month'},
xaxis={'title': 'year'},
hovermode="x")
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
csv_path = find_raw_csv_path('mpg.csv')
df = pd.read_csv(csv_path)
dim = 'mpg'
x_series = df[dim]
x_min, x_max = x_series.min(), x_series.max()
size = request_arg('size', 2, int, lambda x: x in range(int(x_max + 1)))
data = [
go.Histogram(
x=x_series,
xbins=dict(start=min(0, x_min), end=x_max, size=size),
)
]
layout = go.Layout(title="MPG Histogram",
yaxis={'title': dim},
xaxis={'title': 'bins'},
hovermode="x")
fig = go.Figure(data=data, layout=layout)
return fig
def draw():
data_sources = [
'2010YumaAZ.csv', '2010SantaBarbaraCA.csv', '2010SitkaAK.csv'
]
rows = 3
cols = 1
plot_height = 500
vertical_spacing = 0.04
fig = tools.make_subplots(
rows=rows,
cols=cols,
start_cell='top-left', # 'top-left', 'bottom-left'
shared_yaxes=False,
shared_xaxes=False,
# specs=[[{}, {}, {}]],
# vertical_spacing=vertical_spacing,
# horizontal_spacing=0.001,
subplot_titles=[
' '.join((name.rsplit('.', 1)[0][:4], name.rsplit('.', 1)[0][4:-2],
name.rsplit('.', 1)[0][-2:])) for name in data_sources
])
dfs = []
min_z = 0
max_z = 0
for index, data_source in enumerate(data_sources):
df = pd.read_csv(find_raw_csv_path(data_source))
dfs.append(df)
min_z = df['T_HR_AVG'].min() if index == 0 else min(
min_z, df['T_HR_AVG'].min())
max_z = df['T_HR_AVG'].max() if index == 0 else max(
max_z, df['T_HR_AVG'].max())
round_by = 5
min_z = (int(min_z / round_by) + 0) * round_by
max_z = (int(max_z / round_by) + 1) * round_by
colorscale = np.random.choice([
'Greys', 'YlGnBu', 'Greens', 'YlOrRd', 'Bluered', 'RdBu', 'Reds',
'Blues', 'Picnic', 'Rainbow', 'Portland', 'Jet', 'Hot', 'Blackbody',
'Earth', 'Electric', 'Viridis', 'Cividis'
])
data = [
go.Heatmap(
x=df['DAY'].map(lambda x: x[0:3]),
y=df['LST_TIME'],
z=df['T_HR_AVG'],
colorscale=colorscale,
name=data_sources[idx].rsplit('.', 1)[0][4:-2],
zmin=min_z,
zmax=max_z,
) for idx, df in enumerate(dfs)
]
for index, trace in enumerate(data):
fig.append_trace(trace, ((index + 1) // (cols + 1)) + 1,
cols - ((index + 1) % cols))
fig.layout.update(
# height=rows * plot_height + (rows + 1) * vertical_spacing,
title=f"Temperature ({colorscale})", )
return fig