def __create_world_map_chart(self, data, type):
source = alt.topo_feature(dt.world_110m.url, "countries")
base = (
alt.Chart(source, title="")
.mark_geoshape(fill="lightgray", stroke="white")
.properties(width=800, height=450)
.project("equirectangular")
)
points = (
alt.Chart(data[data["variable"] == data["variable"].unique().max()])
.mark_circle()
.encode(
longitude="Long:Q",
latitude="Lat:Q",
size=alt.Size(
"value:Q",
title="Number of Cases",
scale=alt.Scale(range=[250, 2000]),
# legend=None,
),
color=alt.Color("value", scale=alt.Scale(scheme="orangered")),
tooltip=[
alt.Tooltip("Country/Region:N"),
alt.Tooltip("value:Q", format=",.0f"),
],
)
)
chart = base + points
chart = chart.configure_legend(orient="bottom")
return chart.to_html()
def visualize_freq(output_path):
data = pd.read_csv(output_path)
data['year'] = data.htrc_vol.str.split('_').str[2]
data['months'] = data.htrc_vol.str.split('_').str[3]
data['first_month'] = data.months.str.split('-').str[0]
data['second_month'] = data.months.str.split('-').str[1]
data['second_month'].fillna('dec', inplace=True)
data.first_month = data.first_month.str.capitalize()
data.second_month = data.second_month.str.capitalize()
data['first_month_index'] = pd.to_datetime(data['first_month'],
format='%b',
errors='coerce').dt.month
data['second_month_index'] = pd.to_datetime(data['second_month'],
format='%b',
errors='coerce').dt.month
data = data.sort_values(by=['year', 'first_month_index'])
data.htrc_vol.str.split('_')
data['date'] = pd.to_datetime(data['year'].apply(str) + '-' +
data['first_month_index'].apply(str),
format='%Y-%m')
data.date = data.date.dt.strftime('%Y-%m')
data = data[data['frequency'] > 3]
chart = alt.Chart(data).mark_circle(
opacity=0.8, stroke='black', strokeWidth=1).encode(
alt.X('date:O'), alt.Y('word', axis=alt.Axis(labelAngle=0)),
alt.Size('frequency',
scale=alt.Scale(range=[0, 2000]),
legend=alt.Legend(title='counts')),
alt.Color('word',
scale=alt.Scale(scheme='category20'),
legend=None)).properties(width=1400, height=10000)
chart.serve()
def plot_heatmap(mat, str_tit):
ncat_men, ncat_women = mat.shape
mat_arr = np.empty((mat.size, 4))
mat_min, mat_max = np.min(mat), np.max(mat)
i = 0
for ix in range(ncat_men):
for iy in range(ncat_women):
m = mat[ix, iy]
s = m - mat_min + 1
mat_arr[i, :] = np.array([ix, iy, m, s])
i += 1
mat_df = pd.DataFrame(mat_arr, columns=['Men', 'Women', 'Value', 'Size'])
mat_df = mat_df.astype(dtype={
'Men': int,
'Women': int,
'Value': float,
'Size': float
})
base = alt.Chart(mat_df).encode(x='Men:O',
y=alt.Y('Women:O', sort="descending"))
mat_map = base.mark_circle(opacity=0.4).encode(
size=alt.Size('Size:Q',
legend=None,
scale=alt.Scale(range=[1000, 10000])),
color=alt.Color('Value:Q'),
# tooltip=alt.Tooltip('Value', format=".2f")
)
text = base.mark_text(baseline='middle',
fontSize=16).encode(text=alt.Text('Value:Q',
format=".2f"), )
both = (mat_map + text).properties(title=str_tit, width=500, height=500)
return both
def plot_scatter_alt(
self,
color='run:Q',
color_scheme='purplebluegreen',
shape='method:N',
width=400,
height=400,
):
"""Plot the trials total flops vs max size.
"""
import altair as alt
df = self.to_df()
scatter = (alt.Chart(df).mark_point().encode(
x=alt.X('size:Q', title='log2[SIZE]', scale=alt.Scale(zero=False)),
y=alt.Y('flops:Q', title='log10[FLOPS]', scale=alt.Scale(zero=False)),
size=alt.Size(
'random_strength:Q',
scale=alt.Scale(range=[50, 150], type='log'),
legend=None,
),
shape=alt.Shape(shape),
color=alt.Color(color, scale=alt.Scale(scheme=color_scheme)),
tooltip=list(df.columns)))
return (scatter.properties(
width=width,
height=height,
).configure_axis(gridColor='rgb(248, 248, 248)')).interactive()
def plot_contractions_alt(
tree,
x='peak-size',
y='flops',
color='stage',
size='scaling',
width=400,
height=400,
point_opacity=0.8,
color_scheme='lightmulti',
x_scale='log',
y_scale='log',
color_scale='log',
size_scale='linear',
):
import altair as alt
df = tree_to_df(tree)
chart = alt.Chart(df)
encoding = chart.encode(
x=alt.X(x, scale=alt.Scale(type=x_scale, padding=10)),
y=alt.Y(y, scale=alt.Scale(type=y_scale, padding=10)),
color=alt.Color(color,
scale=alt.Scale(scheme=color_scheme,
type=color_scale)),
size=alt.Size(size, scale=alt.Scale(type=size_scale)),
tooltip=list(df.columns),
)
plot = encoding.mark_point(opacity=point_opacity)
return (plot.configure_axis(gridColor='rgb(248,248,248)').properties(
width=width, height=height).interactive())
def projects_hours_days(df):
"""
"""
df_copy = df.copy()
single = alt.selection_single()
chart = alt.Chart(
df_copy, title='Projects').mark_point(filled=True).encode(
alt.X('yearmonthdate(start)', title="Project starting date"),
alt.Y('days', title='Days since the start'),
color=alt.Color(
'status:N',
title='Project current status',
sort='descending',
),
size=alt.Size('hours',
title='Total hours invested in the project'),
tooltip=[
alt.Tooltip('category', title='Category'),
alt.Tooltip('project', title='Project'),
alt.Tooltip('start', title='Project starting date'),
alt.Tooltip('status', title='Status'),
alt.Tooltip('days', title='Days since the start'),
alt.Tooltip('working_days',
title='Days with at least 1 pomodoro'),
alt.Tooltip('hours', title='Total hours invested'),
alt.Tooltip('pomodoros', title='Amount of pomodoros made')
]).add_selection(single).properties(width=800).interactive()
return chart
def chart_troops_paths(troops, advancing=True):
if advancing:
domain = CFG['AdvDomain'].split(',')
else:
domain = CFG['RetDomain'].split(',')
colors = CFG['AdvColors'].split(',') + CFG['RetColors'].split(',')
return alt.Chart(troops).mark_trail(order=False).encode(
x=alt.X('LONP:Q',
scale=alt.Scale(
domain=[troops["LONP"].min(), troops["LONP"].max()]),
axis=alt.Axis(title=None,
labels=False,
grid=True,
gridColor=CFG['TempGridColor'])),
longitude='LONP:Q',
latitude='LATP:Q',
size=alt.Size('SURV',
scale=alt.Scale(
range=[int(i)
for i in CFG['TroopScale'].split(',')]),
legend=None),
color=alt.Color('DIV',
scale=alt.Scale(domain=domain, range=colors),
legend=None),
tooltip=[
alt.Tooltip('SURV', title='Troop Numbers'),
alt.Tooltip('DIR', title='Direction'),
alt.Tooltip('LONP', title='Longitude'),
alt.Tooltip('LATP', title='Latitude')
])
def make_interactive_chart():
'''
'''
pts = alt.selection(type="single", encodings=['x'])
rect = alt.Chart(data.movies.url).mark_rect().encode(
alt.X('IMDB_Rating:Q', bin=True),
alt.Y('Rotten_Tomatoes_Rating:Q', bin=True),
alt.Color('count()',
scale=alt.Scale(scheme='greenblue'),
legend=alt.Legend(title='Total Records')))
circ = rect.mark_point().encode(
alt.ColorValue('grey'),
alt.Size('count()', legend=alt.Legend(
title='Records in Selection'))).transform_filter(pts)
bar = alt.Chart(data.movies.url).mark_bar().encode(
x='Major_Genre:N',
y='count()',
color=alt.condition(pts, alt.ColorValue("steelblue"),
alt.ColorValue("grey"))).properties(selection=pts,
width=550,
height=200)
return alt.vconcat(rect + circ, bar).resolve_legend(color="independent",
size="independent")
def plot_stocks(state, list_of_stocks):
for stock in list_of_stocks:
i = [i for i, _ in enumerate(state.products) if _['name'] == stock][0]
name = state.products[i]['name']
transactions = state.products[i]['transactions'].copy()
historical_data = state.products[i]['historical_data']
general_data = state.products[i]['general_data']
st.write(f'## {name}')
st.write('### General Data')
show_general_data(general_data)
st.write('### Transactions')
st.write(transactions)
st.write('### Historical Data')
if historical_data is None:
st.warning('Couldn\'t get historical data')
else:
transactions.totalPlusFeeInBaseCurrency = (
transactions.totalPlusFeeInBaseCurrency.abs())
line = alt.Chart(historical_data).mark_line().encode(x='date:T',
y='price:Q')
circle = alt.Chart(transactions).mark_circle().encode(
x=alt.X('date:T', title='Date'),
y=alt.Y('price:Q', title='Price'),
size=alt.Size('totalPlusFeeInBaseCurrency', legend=None),
tooltip=['quantity', 'totalPlusFeeInBaseCurrency'],
color=alt.Color(
'buysell',
legend=alt.Legend(title='Buy/Sell'),
scale=alt.Scale(scheme='dark2'))).interactive()
st.altair_chart(line + circle, use_container_width=True)
def plot_anomalies(df, title='Anomaly detection'):
interval = alt.Chart(df).mark_area(interpolate="basis", color='#7FC97F').encode(
x='ds:T',
y='yhat_lower',
y2='yhat_upper',
tooltip=['ds:T', 'y', 'yhat_lower', 'yhat_upper']
).interactive().properties(
title=title
)
y = alt.Chart(df[df.anomaly == 0]).mark_circle(size=15, opacity=0.9, color='Black').encode(
x='ds:T',
y='y',
tooltip=['ds:T', 'y', 'yhat_lower', 'yhat_upper']
).interactive()
anomalies = alt.Chart(df[df.anomaly != 0]).mark_circle(size=30, color='Red').encode(
x='ds:T',
y='y',
tooltip=['ds:T', 'y', 'yhat_lower', 'yhat_upper'],
size=alt.Size('importance', legend=None)
).interactive()
anomaly_chart = alt.layer(interval, y, anomalies) \
.properties(width=870, height=450) \
.configure_title(fontSize=20)
anomaly_chart.save('./test/anomaly_chart.html')
def plot_anomalies(forecasted, chart_title=''):
interval = alt.Chart(forecasted).mark_area(
interpolate="basis", color='#7FC97F').encode(
x=alt.X('ds:T', title='date'),
y='yhat_upper',
y2='yhat_lower',
tooltip=['ds', 'fact', 'yhat_lower', 'yhat_upper'
]).interactive().properties(title=chart_title +
' Anomaly Detection')
fact = alt.Chart(forecasted[forecasted.anomaly == 0]).mark_circle(
size=15, opacity=0.7, color='Black').encode(
x='ds:T',
y=alt.Y('fact', title='sales'),
tooltip=['ds', 'fact', 'yhat_lower', 'yhat_upper']).interactive()
anomalies = alt.Chart(forecasted[forecasted.anomaly != 0]).mark_circle(
size=30,
color='Red').encode(x='ds:T',
y=alt.Y('fact', title='sales'),
tooltip=['ds', 'fact', 'yhat_lower', 'yhat_upper'],
size=alt.Size('importance',
legend=None)).interactive()
return alt.layer(interval, fact, anomalies)\
.properties(width=870, height=450)\
.configure_title(fontSize=20)
def plot(self,position:str, test_df = None):
data = self.target_data().copy()
data["test"] = False
if test_df is not None:
test_df["test"] = True
data = pd.concat([data, test_df]).reset_index()
data = data.query(f"id == '{position}'").copy()
x = np.arange(data["depth"].min(), data["depth"].max(), 1000).reshape(-1,1)
y = self.linear_models[position].predict(x)
y_seuil = x * 0.005
line = pd.DataFrame({"x":x.reshape(-1), "y":y.reshape(-1)})
line2 = pd.DataFrame({"x":x.reshape(-1), "y":y_seuil.reshape(-1)})
data["fraction"] = data["second_vaf"] / data["depth"] * 100
data["s"] = data["sample"].str.replace(r"-\d","", regex=True)
data["outlier"] = self.outlier_models[position].predict(data[["depth","second_vaf"]])
c1 = alt.Chart(data).mark_circle(color="green").encode(
x="depth",
y="second_vaf",
size=alt.Size("test", scale = alt.Scale(type = "ordinal", range=[50, 400])),
color=alt.Color("test", scale = alt.Scale(range=["gray","green"])),
tooltip = ["file","sample","depth","fraction", "outlier"])
c2 = alt.Chart(line).mark_line(color="green",strokeDash=[1,3]).encode(x="x",y="y")
c3 = alt.Chart(line2).mark_line(color="red", strokeDash=[1,3]).encode(x="x",y="y")
return (c1 + c2 + c3).interactive()
def generate_align_vs_features(data_frame, output_folder, file_name):
"""
Generates a chart of the relation between align and other features in dataset.
Also saves resulting image as file in given output folder.
Parameters:
-----------
data_frame : pandas.DataFrame
input path to be verified
output_folder : str
output folder path to save the chart
file_name : str
file name for generated chart image
Returns:
-----------
None
"""
features = ['id', 'eye', 'hair', 'sex', 'gsm', 'publisher']
align_vs_features = (alt.Chart(data_frame).mark_circle().encode(
alt.Y(alt.repeat(), type='ordinal'),
alt.X('count()', title = "Character Count"),
size =alt.Size('count()', legend=alt.Legend(title="Characters")),
color = alt.Color("align", legend=alt.Legend(title="Alignment"))
).properties(height=300, width=200).repeat(repeat=features, columns=3))
save(align_vs_features, output_folder +"/figures/" + file_name + '.png', method='selenium', webdriver=driver)
if verbose: print("Alignment vs features chart created, saved to " +
output_folder +
"/figures/" +
file_name +
'.png')
def visualise_tsne(tsne_df, save=True, fig_num=15):
"""Visualise tsne plot"""
tsne_base = alt.Chart(tsne_df).encode(
x=alt.X("x:Q", title="", axis=alt.Axis(ticks=False, labels=False)),
y=alt.Y("y:Q", title="", axis=alt.Axis(ticks=False, labels=False)),
)
tsne_points = ((
tsne_base.mark_point(
filled=True, opacity=0.5, stroke="black",
strokeOpacity=0.5).encode(
color=alt.Color("org_type", title="Organisation type"),
strokeWidth=alt.Stroke("top",
scale=alt.Scale(range=[0, 1]),
legend=None),
# stroke = alt.value('blue'),
size=alt.Size("activity:Q", title="Number of papers"),
facet=alt.Facet("size",
columns=2,
title="Number of organisations in plot"),
tooltip=["index"],
)).interactive().resolve_scale(
y="independent", x="independent").properties(width=250,
height=250))
if save is True:
save_altair(tsne_points, "fig_15_tsne", driv)
return tsne_points
def plot_suicide_gdp(data, sex, country, age, year):
alt.themes.enable('dark')
df = data[data['country'] == country]
#for gender in sex:
#if type(sex) == 'str':
#df = df[df['sex'] == sex]
if not type(sex) == list:
df = df[df['sex'] == sex]
else:
pass
df = df[df['age'] == age]
# df = df[df['generation'] == generation]
df['year'] = pd.to_datetime(df['year'], format='%Y')
year = pd.to_datetime(year, format='%Y')
df = df[df['year'] > year[0]]
df = df[df['year'] < year[1]]
chart = alt.Chart(df, title='Suicide Trends per Country').mark_circle(
color='yellow').encode(alt.X('year', title='Year'),
alt.Y('suicides_no',
title='Total Number of Suicides'),
alt.Color('sex',
scale=alt.Scale(scheme='blueorange')),
alt.Size('gdp_per_capita ($):Q', legend=None),
tooltip=[
alt.Tooltip('country:N'),
alt.Tooltip('gdp_per_capita ($):Q')
]).interactive().configure_axis(grid=False)
return chart.to_html()
def get_map(self, day_str, title=""):
chart_data = self._prepare_dataset(day_str)
source = alt.topo_feature(data.world_110m.url, 'countries')
background = alt.Chart(source).mark_geoshape(
fill="lightgray",
stroke="white").properties(width=1000,
height=500).project("equirectangular")
hover = alt.selection(type='single',
on='mouseover',
nearest=False,
fields=[self.col_lat, self.col_long])
text = background.mark_text(dy=-5, align='right').encode(
alt.Text(f'{self.col_name_countries}:N', type='nominal'),
opacity=alt.condition(~hover, alt.value(0), alt.value(1)))
points = alt.Chart(chart_data).mark_circle().encode(
latitude=f"{self.col_lat}:Q",
longitude=f"{self.col_long}:Q",
size=alt.Size(f"{day_str}:Q",
scale=alt.Scale(range=[0, 7000]),
legend=None),
order=alt.Order(f"{day_str}:Q", sort="descending"),
tooltip=[f'{self.col_name_countries}:N', f'{day_str}:Q'
]).add_selection(hover).properties(title=title)
chart = alt.layer(background, points, text)
return chart
def country_plot(source):
alt.themes.enable('dark')
combined11 = source
selection = alt.selection_single()
country_chart = alt.Chart(
combined11,
title='Spread of Countries - GDP Vs Total Suicide Numbers').mark_point(
filled=True).encode(
alt.X('gdp_per_capita:Q'),
alt.Y('suicides_no'),
alt.Size('population:Q',
scale=alt.Scale(range=[0, 2000]),
legend=None),
alt.Order('population:Q', sort='ascending'),
tooltip=[
alt.Tooltip('country:N'),
alt.Tooltip('suicides_no:Q'),
alt.Tooltip('gdp_per_capita:Q'),
alt.Tooltip('population')
],
color=alt.condition(
selection,
'country',
alt.value('darkgrey'),
scale=alt.Scale(scheme='blueorange'),
legend=None)).add_selection(selection).configure_axis(
grid=False)
return country_chart.to_html()
def plot_anomalies(self, forecasted):
"""Show plot with anomalies
Inspired from https://towardsdatascience.com/anomaly-detection-time-series-4c661f6f165f"""
interval = alt.Chart(forecasted).mark_area(
interpolate="basis", color='#adadad').encode(
x=alt.X('ds:T', title='Time'),
y='yhat_upper',
y2='yhat_lower',
tooltip=['ds', 'fact', 'yhat_lower', 'yhat_upper'
]).interactive().properties(title='Anomaly Detection')
fact = alt.Chart(forecasted[forecasted.anomaly == 0]).mark_circle(
size=15, opacity=0.7, color='Black').encode(
x='ds:T',
y=alt.Y('fact', title='CPU Utilization [%]'),
tooltip=['ds', 'fact', 'yhat_lower',
'yhat_upper']).interactive()
anomalies = alt.Chart(forecasted[forecasted.anomaly != 0]).mark_circle(
size=30, color='Red').encode(
x='ds:T',
y=alt.Y('fact', title='CPU Utilization [%]'),
tooltip=['ds', 'fact', 'yhat_lower', 'yhat_upper'],
size=alt.Size('importance', legend=None)).interactive()
return alt.layer(interval, fact, anomalies) \
.properties(width=870, height=450) \
.configure_title(fontSize=20)
def test_shorthand_typecodes(mydata):
opts = {
"xvar": "name",
"yvar": "amount:O",
"fillvar": "max(amount)",
"sizevar": "mean(amount):O",
}
cg = ChannelGroup(opts, mydata)
assert cg == {
"x":
alt.X(**{
"field": "name",
"type": "nominal"
}),
"y":
alt.Y(**{
"field": "amount",
"type": "ordinal"
}),
"fill":
alt.Fill(**{
"field": "amount",
"type": "quantitative",
"aggregate": "max",
}),
"size":
alt.Size(**{
"field": "amount",
"type": "ordinal",
"aggregate": "mean",
}),
}
def punchcode():
dat = df.copy()
dat['mnth_yr'] = dat['workshop_start'].dt.to_period('M').astype(str)
dat['workshop_category'] = dat['workshop_category'].apply(
lambda x: 'Corporate' if (x == 'Corporate') else 'Public')
dat['contrib'] = dat['workshop_hours'] * dat['class_size']
chart = alt.Chart(
dat[dat.name != 'Capstone']).mark_circle(color='#bbc6cbe6').encode(
x=alt.X('mnth_yr:T', axis=alt.Axis(title='')),
y='name:O',
size=alt.Size('sum(contrib):Q', legend=None),
column=alt.Column('workshop_category:O',
title=None,
sort="descending",
header=alt.Header(titleColor='#bbc6cbe6',
labelColor='#bbc6cbe6',
labelAngle=30,
titleFontSize=40,
titleAngle=30))).properties(
width=300,
height=320).configure_axis(
labelColor='#bbc6cbe6',
titleColor='#bbc6cbe6',
grid=False)
return chart.to_json()
def world_map(highlight, highlight2):
slider = alt.binding_range(min=1991, max=2011, step=1)
select_year = alt.selection_single(name="Year",
fields=['Year'],
bind=slider,
init={'Year': 2011})
map = alt.Chart(df).mark_geoshape(stroke='#aaa', strokeWidth=0.25).encode(
color=alt.condition(highlight2 | highlight,
'CO2 emissions (kt):Q',
alt.value('lightgrey'),
scale=alt.Scale(scheme='redyellowblue',
reverse=True)),
tooltip=[
"Country Name", "CO2 emissions (kt)", "CO2 emissions per capita"
]
).transform_lookup(
lookup='Country Name',
from_=alt.LookupData(
"https://raw.githubusercontent.com/KoGor/Map-Icons-Generator/master/data/world-110m-country-names.tsv",
'name', ['id', "name"])).transform_lookup(
lookup='id',
from_=alt.LookupData(
countries,
'id',
fields=["id", "type", "properties", "geometry"])
).project(type="equirectangular").properties(
width=1100,
height=650,
title='worldwide CO2 total emissions and emissions per capita'
).add_selection(highlight, highlight2)
percapita = alt.Chart(df).mark_circle(opacity=0.4, ).encode(
size=alt.Size('CO2 emissions per capita:Q',
scale=alt.Scale(range=[10, 3000])),
color=alt.condition(highlight2 | highlight, alt.value('red'),
alt.value('lightgrey')),
longitude='Longitude (average):Q',
latitude='Latitude (average):Q',
tooltip=[
"Country Name", "CO2 emissions (kt)", "CO2 emissions per capita"
]
).transform_lookup(
lookup='Country Name',
from_=alt.LookupData(
"https://raw.githubusercontent.com/KoGor/Map-Icons-Generator/master/data/world-110m-country-names.tsv",
'name', ['id', "name"])).transform_lookup(
lookup='id',
from_=alt.LookupData(
countries,
'id',
fields=["id", "type", "properties", "geometry"
])).project(type="equirectangular").properties(
width=900,
height=400,
)
return alt.layer(map, percapita) \
.add_selection(select_year) \
.transform_filter(select_year)
def scatter_plot(df, picked_interval, single_select):
point = alt.Chart(df).mark_circle().encode(
x=alt.X('Year:O', title="Year"),
y=alt.Y('CO2 emissions (kt)',
title='Total CO2 emissions (kt)',
scale=alt.Scale(zero=False, padding=1)),
# color = alt.Color('Country Name:N',scale=alt.Scale(domain=dataset,type='ordinal'))
# color = alt.Color('CO2 emissions (kt):Q')
color=alt.condition(picked_interval | single_select,
"CO2 emissions (kt):Q",
alt.value("lightgray"),
scale=alt.Scale(scheme='redyellowblue',
reverse=True),
title="Total CO2 emissions (kt)"),
size=alt.Size('CO2 emissions per capita:Q',
scale=alt.Scale(range=[300, 1000])),
tooltip=[
"Country Name", "CO2 emissions (kt)", "CO2 emissions per capita",
"Year"
]).add_selection(single_select)
line = alt.Chart(df).mark_line(
# strokeWidth=0.7
).encode(
x=alt.X('Year:N', title="Year"),
y=alt.Y('CO2 emissions (kt):Q', title='Total CO2 emissions (kt)'),
color=alt.condition(picked_interval | single_select,
"Country Name",
alt.value("lightgray"),
legend=None),
# color = alt.Color('CO2 emissions (kt):Q')
# color=alt.condition(picked_interval, "CO2 emissions (kt):Q", alt.value("lightgray"),
# scale=alt.Scale(scheme='redyellowblue', reverse=True), title="Total CO2 emissions (kt)")
size=alt.condition(~(picked_interval | single_select), alt.value(1),
alt.value(3)),
tooltip=[
"Country Name", "CO2 emissions (kt)", "CO2 emissions per capita",
"Year"
]).properties(
width=650,
height=500,
title='CO2 total emission and emission per capita overtime')
labels = alt.Chart(df).mark_text(align='center', dx=-20, dy=-25).encode(
alt.X('Year:O', aggregate='max'),
alt.Y('CO2 emissions (kt)', aggregate={'argmax': 'Year'}),
alt.Text('Country Name'),
alt.Color('CO2 emissions (kt):Q',
aggregate={'argmax': 'Year'},
scale=alt.Scale(scheme='redyellowblue', reverse=True),
legend=None),
size=alt.condition(~(single_select), alt.value(17), alt.value(20)),
).properties(title='CO2 total emission and emission per capita', width=600)
points = line + point + labels
return points
def map_state(curr_day_num, state_txt, state_counties, confirmed,
confirmed_min, confirmed_max, deaths, deaths_min, deaths_max):
# Washington State
base_state = alt.Chart(state_counties).mark_geoshape(
fill='white',
stroke='lightgray',
).properties(
width=1000,
height=800,
).project(type='mercator')
# counties
base_state_counties = alt.Chart(
us_counties).mark_geoshape().transform_lookup(
lookup='id',
from_=alt.LookupData(
confirmed[(confirmed['confirmed'] > 0)
& (confirmed['day_num'] == curr_day_num)], 'fips',
['confirmed', 'county'])).encode(
color=alt.Color('confirmed:Q',
scale=alt.Scale(
type='log',
domain=[confirmed_min, confirmed_max]),
title='Confirmed'),
tooltip=[
alt.Tooltip('confirmed:Q'),
alt.Tooltip('county:O'),
],
)
# deaths by long, latitude
points = alt.Chart(
deaths[(deaths['deaths'] > 0) & (deaths['day_num'] == curr_day_num)]
).mark_point(opacity=0.75, filled=True).encode(
longitude='long_:Q',
latitude='lat:Q',
size=alt.Size('sum(deaths):Q',
scale=alt.Scale(type='symlog',
domain=[deaths_min, deaths_max]),
title='deaths'),
color=alt.value('#BD595D'),
stroke=alt.value('brown'),
tooltip=[
alt.Tooltip('lat'),
alt.Tooltip('long_'),
alt.Tooltip('deaths'),
alt.Tooltip('county:O'),
],
).properties(
# update figure title
title=
f'COVID-19 {state_txt} Confirmed Cases and Deaths per 100K by County [{curr_day_num}]'
)
return (base_state + base_state_counties + points)
def status_by_dep_arr():
selection = alt.selection_multi(fields=['STATUS'])
brush = alt.selection(type='interval')
color_select_brush = alt.condition(selection | brush,
alt.Color('STATUS:N', legend=None),
alt.value('lightgrey'))
color_select = alt.condition(selection, alt.Color('STATUS:N', legend=None),
alt.value('lightgrey'))
# color_brush = alt.condition(brush,
# alt.Color('STATUS:N', legend = None),
# alt.value('lightgray'))
dep_arr = alt.Chart(df).mark_circle().encode(
# dep_arr = alt.Chart(df).mark_circle().transform_filter(alt.datum['STATUS'] != 'on time').encode(
x = alt.X('CRS_DEP_TIME:Q', title = 'Departure Time', axis = alt.Axis(labelOverlap = True)),
y = alt.Y('CRS_ARR_TIME:Q', title = 'Arrival Time', axis = alt.Axis(labelOverlap = True), sort = '-y'),
# color = alt.condition(brush, 'STATUS', alt.value('lightgray')),
color = color_select_brush,
size = alt.Size('average(ARR_DELAY):Q', title = 'Arrival Delay', scale = alt.Scale(domain = [1, 800]), legend = None),
tooltip = [alt.Tooltip('CRS_DEP_TIME', title = 'Departure Time'), alt.Tooltip('CRS_ARR_TIME', title = 'Arrival Time'), \
alt.Tooltip('average(ARR_DELAY):Q', title = 'Arrival Delay')],
).add_selection(brush).properties(width = 600, height = 400)
bars = alt.Chart(df).mark_bar().encode(
# bars = alt.Chart(df).mark_bar().transform_filter(alt.datum['STATUS'] != 'on time').encode(
y=alt.Y('STATUS', title=''),
# color = 'STATUS',
color=color_select,
x=alt.X('count(STATUS):Q', title='Delayed Flights Count'),
).transform_filter(brush)
bar_text = bars.mark_text(
align='left',
baseline='middle',
dx=3 # Nudges text to right so it doesn't appear on top of the bar
).encode(text='count(STATUS):Q')
# count = alt.Chart(df).mark_bar().encode(
count = alt.Chart(df).mark_bar().transform_filter(
alt.datum['STATUS'] != 'on time').encode(x=alt.X(
'count(STATUS):Q',
title='Total Delayed Flights Count'), ).transform_filter(brush)
count_text = count.mark_text(align='left', baseline='middle',
dx=3).encode(text='count(STATUS):Q')
legend = alt.Chart(df).mark_point().encode(
# legend = alt.Chart(df).mark_point().transform_filter(alt.datum['STATUS'] != 'on time').encode(
y=alt.Y('STATUS:N', axis=alt.Axis(orient='right')),
color=color_select).add_selection(selection)
(dep_arr & (count + count_text) & (bars + bar_text)) | legend
def bubble_chart(df, year):
df_year = df[df['year'] == year].copy()
alt_chart = alt.Chart(df_year).mark_circle().encode(
alt.X('gdpPercap:Q', scale=alt.Scale(type='log',
domain=(100, 100000))),
alt.Y('lifeExp:Q', scale=alt.Scale(domain=(25, 90))),
size=alt.Size('pop:Q'),
color='continent:N',
tooltip=['country', 'lifeExp', 'pop',
'gdpPercap']).properties(title=str(year)).interactive()
return alt_chart
def chart_obj(request):
h_list = Homicide.objects.annotate(c=Count('count')).values(
'age', 'c', 'gender')
data = alt.Data(values=list(h_list))
chart = alt.Chart(data, height=300, width=300,
title='Age / Gender').mark_circle().encode(
alt.X('age:Q', bin=True),
alt.Y('gender:N'),
alt.Size('sum(c):Q', title='Counts'),
color='sum(c):Q')
return JsonResponse(chart.to_dict(), safe=False)
def plot_chart4(level):
chart = alt.Chart(hr4[hr4.experience_level == level]).mark_point().encode(
alt.X("education_level", title="Educaiton Level"),
alt.Y("major_discipline", title="Major Discipline"),
alt.Size("mean(target)", legend=alt.Legend(title="Change Job Ratio")),
alt.Color("mean(target)"),
fill="mean(target)",
).properties(width=400, height=400)
chart = alt.layer(chart).configure_axis(
labelFontSize=16, titleFontSize=20).configure_legend(labelFontSize=16,
titleFontSize=16)
return chart.to_html()
def punchcard_repo(ds):
ds.engine = "altair"
ds.rcolor()
ds.width(630)
ds.height(15)
ds.chart("Date:T", "Repository:N")
ds.aenc("size", alt.Size('Commits', legend=None))
c = ds.square_().configure_axis(
titleColor="transparent", grid=False, tickSize=0,
domain=False, labelFontSize=0).configure_view(strokeWidth=0)
ds.raencs()
return c
def app():
st.title("Let's demo Streamlit basics")
st.sidebar.markdown("**Some tools we'll use:**")
st.sidebar.markdown("""
* Markdown
* Pandas
* Altair""")
st.markdown("""## Markdown and Pandas
I am writing Markdown but I can also show a pandas DataFrame.
""")
df_cars = data.cars()
st.write(df_cars.head())
st.markdown("""## Altair
And I can easily make interactive altair plots.
""")
brush = alt.selection_interval(encodings=['x', 'y'])
repeat_chart = alt.Chart(df_cars).mark_point().encode(
alt.X(alt.repeat('column'), type='quantitative'),
alt.Y('Miles_per_Gallon:Q'),
color=alt.condition(brush, 'Origin:N', alt.value('lightgray')),
opacity=alt.condition(
brush, alt.value(0.7), alt.value(0.1))).properties(
width=150, height=150).add_selection(brush).repeat(
column=['Weight_in_lbs', 'Acceleration', 'Horsepower'])
st.write(repeat_chart)
st.markdown("""## User Input
I can create a text input field to get input from the user.
""")
n = int(st.text_input("How many points do you want plotted:", '100'))
x = np.random.random(n) * 10
y = np.random.random(n) * 10
s = np.random.random(n)
df = pd.DataFrame({'x': x, 'y': y, 'size': s})
chart = alt.Chart(df, width=400,
height=400).mark_point().encode(
x='x',
y='y',
size=alt.Size('size', legend=None),
tooltip=['size']).interactive()
st.write(chart)
def show_chart(data,items):
stat = {'rank':'Rank','All Employees':'All Employees (1K)','Avg Hourly Wages':'Avg Hourly Wages','eWage':'Pricing Power','score':'Employment Strengths','eCPI':'Price Index'}
stat_text = list(stat.values())
stat_keys = list(stat.keys())
items = [key for key, value in items.items() if value!=0]
data = data[['year','cbsa_area','Metro area']+stat_keys+items]
st.subheader('Employment strengths')
# Employment strengths scatter
scatter = (alt.Chart(data)
.mark_circle()
.encode(
x=alt.X(stat_keys[1],title=stat_text[1]),
y=alt.Y(stat_keys[2],title=stat_text[2]),
size=alt.Size(stat_keys[4],legend=None),
tooltip=[alt.Tooltip('Metro area'),alt.Tooltip(stat_keys[0],title=stat_text[0]),alt.Tooltip(stat_keys[1],title=stat_text[1]),alt.Tooltip(stat_keys[2],title=stat_text[2],format='$')]
)
)
st.altair_chart(scatter,use_container_width=True)
st.subheader('Price Index')
# Price Index stacked_bar
stacked_cpi = (alt.Chart(data)
.transform_fold(items,['Item','Price Index'])
.mark_bar()
.encode(
x=alt.X('Price Index:Q'),
y=alt.Y('Metro area:N',sort=alt.EncodingSortField(field=stat_keys[5],order='descending')),
color=alt.Color('Item:N'),
tooltip=[alt.Tooltip('Metro area'),alt.Tooltip('Item:N'),alt.Tooltip('Price Index:Q'),alt.Tooltip(stat_keys[5],title=stat_text[5])]
)
)
st.altair_chart(stacked_cpi,use_container_width=True)
st.subheader('Pricing Power')
# Employment strengths scatter
stacked_pp = (alt.Chart(data)
.mark_bar()
.encode(
x=alt.X(stat_keys[3],title=stat_text[3]),
y=alt.Y('Metro area:N',sort=alt.EncodingSortField(field=stat_keys[3],order='descending')),
tooltip=[alt.Tooltip('Metro area'),alt.Tooltip(stat_keys[2],title=stat_text[2]),alt.Tooltip(stat_keys[5],title=stat_text[5]),alt.Tooltip(stat_keys[3],title=stat_text[3])]
)
)
st.altair_chart(stacked_pp,use_container_width=True)
