def perfect_subset_overlap_summary(df: DataFrame) -> alt.Chart:
"""Summarize the count of instances of parent/child overlap by NLA (parent greater, equal, child greater)
"""
top_bar = alt.Chart(df).mark_bar().encode(
x=alt.X('count(parent)',
stack='normalize',
axis=None,
sort=[
'parent nla greater than child',
'parent and child nla equal', 'parent nla less than child'
]),
color=alt.Color('nla_variance', scale=alt.Scale(scheme='greys')),
order=alt.Order('nla_variance',
sort='ascending')).properties(width=600, height=75)
text = alt.Chart(df).mark_text(dx=-15, dy=0, color='white').encode(
x=alt.X('count(parent):Q',
stack='normalize',
axis=None,
sort=[
'parent nla greater than child',
'parent and child nla equal', 'parent nla less than child'
]),
detail='nla_variance:N',
text=alt.Text('count(parent):Q', format='.0f'),
order=alt.Order('nla_variance', sort='ascending'))
top_chart = top_bar + text
return top_chart
def Joint_Prob_plot(df):
year_min = df["cohort"].min()
year_max = df["cohort"].max()
slider = alt.binding_range(min=year_min, max=year_max, step=1)
select = alt.selection_single(name="year",
fields=['cohort'],
bind=slider,
init={'cohort': year_min})
df_new = df.apply(lambda row: gen_plot_df(row), axis=1)
df_new = pd.concat(list(df_new))
base = alt.Chart(df_new)
# chart on Joint Prob
plot_scale = alt.Scale(type="pow",
exponent=0.5,
scheme="greens",
nice=True)
color = alt.Color('MR:Q', scale=plot_scale)
joint_chart = base.mark_rect().encode(
x="p:O",
y=alt.Y('k:O', sort=alt.EncodingSortField('k', order='descending')),
color=color).add_selection(select).transform_filter(select).properties(
height=200, width=200)
color_scale = alt.Scale(
domain=['1', '2', '3', '4', '5'],
range=['#4c78a8', '#f58518', '#e45756', '#72b7b2', '#54a24b'])
p_mag_1 = base.mark_bar().encode(
x=alt.X("p:O"),
y=alt.Y('sum(MR):Q', scale=alt.Scale(domain=(0, 1))),
color=alt.Color('k:O', scale=color_scale, legend=None),
order=alt.Order(aggregate='sum',
type="quantitative",
sort='descending')).add_selection(
select).transform_filter(select).properties(
height=150, width=200)
k_mag_1 = base.mark_bar().encode(
y=alt.Y("k:O", sort=alt.EncodingSortField('k', order='descending')),
x=alt.X('sum(MR):Q', scale=alt.Scale(domain=(0, 1))),
color=alt.Color('p:O',
scale=color_scale,
sort=alt.EncodingSortField('p', order='ascending'),
legend=None),
order=alt.Order(aggregate='sum',
type="quantitative",
sort='descending')).add_selection(
select).transform_filter(select).properties(
height=200, width=150)
people_c = people_plot(df, select).properties(width=300, height=300)
return (p_mag_1 & (joint_chart | k_mag_1)
& people_c).resolve_scale(color='independent')
def get_bar_chart(data: pd.DataFrame, plot_title: str, ax_title: str, marker_col: str, value_col: str, color_col:str, bar_width: int = 0):
"""Returns a altair barchart object"""
tooltips = [value_col, marker_col]
if 'Kanton' in data.columns:
tooltips.append('Kanton')
xax_title = 'Kantone'
else:
xax_title = ''
# remove CH total
if y_max == 0:
scy = alt.Scale()
else:
scy = alt.Scale(domain=(0, y_max))
if marker_col == 'Date':
xax=alt.X(f'{marker_col}:T', axis=alt.Axis(title='', labelAngle = 30, format="%d.%m"))
elif marker_col == 'Sterbedatum':
xax=alt.X(f'{marker_col}:T', axis=alt.Axis(title='', labelAngle = 30, format="%d.%m"))
else:
xax = alt.X(f"{marker_col}:O", axis = alt.Axis(title=xax_title))
if 'Kanton' in data.columns:
clr = alt.condition(
alt.datum[color_col] == 'BS',
alt.value('orange'),
alt.value('steelblue'))
else:
clr = alt.Color(color_col,
scale=alt.Scale(scheme=cn.COLOR_SCHEMA))
if bar_width > 0:
bar = alt.Chart(data).mark_bar(width = bar_width).encode(
x=xax,
y=alt.Y(f'{value_col}:Q',
title=ax_title,
scale=scy
),
color = clr,
order=alt.Order(color_col, sort='ascending'),
tooltip=tooltips)
else:
bar = alt.Chart(data).mark_bar().encode(
x=xax,
y=alt.Y(f'{value_col}:Q',
title=ax_title,
scale=scy
),
color = clr,
order=alt.Order(color_col, sort='ascending'),
tooltip=tooltips)
# not sure why the mean is sometime lower than the minimum bar mean
# rule = alt.Chart(data).mark_rule(color='red').encode(
# y='mean({}):Q'.format(val_par)
chart = bar.properties(width=plot_width, height=plot_height, title=plot_title)
return chart
def show_genre_platform(df):
st.write('## Popular Game Genres on each Platform')
st.write(
"**Let's see how game trends evolve on each platform. Are gamers' preference changing over the decades?**"
)
columns = list(df["Platform"].unique())
select_box = alt.binding_select(options=columns, name='Select a Platform:')
sel = alt.selection_single(fields=['Platform'],
bind=select_box,
init={'Platform': 'Wii'})
# stacked bar chart
st.write(
"💡 *You can select specific platform with the dropdown menu below*")
st.write(
"💡 *Hover over the genres to see their popularities in different regions*"
)
st.write(
alt.Chart(df).transform_filter(sel).mark_bar().encode(
x=alt.X('Year:N'),
y=alt.Y('sum(Global_Sales):Q', title='Sale (in millions)'),
color=alt.Color('Genre', scale=alt.Scale(scheme='tableau20')),
order=alt.Order('Genre', sort='ascending'),
tooltip=[
'Genre', 'sum(NA_Sales)', 'sum(EU_Sales)', 'sum(JP_Sales)',
'sum(Other_Sales)'
]).add_selection(sel).properties(width=800, height=500))
def show_game_publisher(df):
st.write('## Top 20 Best-selling Game for each Company/Publisher')
st.write("**What are the most popular games by each company/publisher?**")
columns = list(df["Publisher"].unique())
select_box = alt.binding_select(options=columns,
name='Select a Publisher:')
sel = alt.selection_single(fields=['Publisher'],
bind=select_box,
init={'Publisher': 'Nintendo'})
# stacked bar chart
st.write(
"💡 *You can select specific publisher/company with the dropdown menu below*"
)
st.write(
"💡 *Hover over the game titles to see their popularities in different regions*"
)
st.write(
alt.Chart(df).transform_filter(sel).mark_bar().encode(
x=alt.X('Year:N'),
y=alt.Y('sum(Global_Sales):Q', title='Sale (in millions)'),
color=alt.Color('Name', scale=alt.Scale(scheme='tableau20')),
order=alt.Order('sum(Global_Sales)', sort='ascending'),
tooltip=[
'Name', 'Genre', 'sum(NA_Sales)', 'sum(EU_Sales)',
'sum(JP_Sales)', 'sum(Other_Sales)'
]).transform_window(
rank="rank(Global_Sales)",
sort=[alt.SortField("Global_Sales", order="descending")
]).transform_filter(
(alt.datum.rank < 20)).add_selection(sel).properties(
width=800, height=500))
def stacked_bar_chart(self):
print(self.data)
chart = (
alt.Chart(self.data, height=450).mark_bar().encode(
x=alt.X("sum(percent)",
stack="normalize",
axis=alt.Axis(format="%")),
y=alt.Y("source", axis=None),
color="item",
tooltip=list(self.data.columns),
order=alt.Order(
# Sort the segments of the bars by this field
"percent",
sort="ascending",
),
).configure_title(fontSize=20).configure_axis(
labelFontSize=10,
titleFontSize=10).configure_legend(labelFontSize=10,
titleFontSize=10))
# text = alt.Chart(self.data).mark_text(dx=-5, dy=3, color='white').encode(
# x=alt.X("sum(percent)", stack="normalize", axis=alt.Axis(format="%")),
# y=alt.Y("source",axis=None),
# detail='item:N',
# text=alt.Text('item')
# )
# full_chart = chart + text
return st.altair_chart(chart, use_container_width=True)
def show_business_in_category(yelp_covid_bool_df, business_category_info):
cat_info_cnt = pd.DataFrame()
feature = st.selectbox("Select a Covid feature you are interested in: ",
total_covid_feature)
for cate in cate_list_multi:
cat_info_cnt[cate] = yelp_covid_bool_df[
business_category_info[cate]].groupby(feature).agg(
{'business_id': 'count'})['business_id']
cat_info_cnt.index = ['False', 'True']
cat_info_cnt = cat_info_cnt.stack().reset_index(level=[0, 1])
cat_info_cnt.columns = [feature, 'categories', 'count']
chart = alt.Chart(cat_info_cnt).mark_bar().encode(
alt.X('count'),
alt.Y('categories:N', sort='-x'),
alt.Color(feature + ':N'),
alt.Tooltip(['count', feature]),
order=alt.Order(feature, sort='descending')).properties(height=200,
width=700)
st.altair_chart(chart)
st.write(
"Of course, different types of businesses react differently. For example, you can see a huge part of Reastaurants and Food support **delivery and takeout**, while **request a quote** is nearly exclusively supported by Home Services."
)
def plot_play_count_graph(info_content_df: pd.DataFrame,
info_userdata_df: pd.DataFrame,
log_problem_df: pd.DataFrame):
st.header("**♟** Difficulty Frequency **♟**")
st.write(
"This page contains basic exploratory data analyses for the purpose of getting a general feeling of what the data contains."
)
chart = alt.Chart(info_content_df).mark_bar().encode(
x='count()',
y='learning_stage',
color='difficulty',
order=alt.Order(
# Sort the segments of the bars by this field
'learning_stage',
sort='ascending')).properties(width=1500, height=200)
st.altair_chart(chart, use_container_width=True)
st.header('Log Problem')
st.write(
'From the chart below, we could see that the number of users attempt the question is getting lower.'
)
datecount_df = (pd.to_datetime(
log_problem_df['timestamp_TW'],
format='%Y-%m-%d %H:%M:%S %Z').dt.floor('d').value_counts(
).rename_axis('date').reset_index(name='count').sort_values('date'))
chart = alt.Chart(datecount_df).mark_line().encode(x='date', y='count')
st.altair_chart(chart, use_container_width=True)
def show_game_series(df):
st.write('## Popular Game Series')
st.write("**Let's explore some of the most popular game series**")
game_series = get_game_series(df)
game_series_df, columns = get_game_series_df(df, game_series)
select_box = alt.binding_select(options=columns,
name='Select a Game Series:')
sel = alt.selection_single(fields=['Series_Name'],
bind=select_box,
init={'Series_Name': 'Pokemon'})
# stacked bar chart
st.write(
"💡 *You can select specific game serie with the dropdown menu below*")
st.write(
"💡 *Hover over the game titles to see their popularities in different regions*"
)
st.write(
alt.Chart(game_series_df).transform_filter(sel).mark_bar().encode(
x=alt.X('Year:N'),
y=alt.Y('sum(Global_Sales):Q', title='Sale (in millions)'),
color=alt.Color('Name', scale=alt.Scale(scheme='tableau20')),
order=alt.Order('Name', sort='ascending'),
tooltip=[
'Name', 'Genre', 'sum(NA_Sales)', 'sum(EU_Sales)',
'sum(JP_Sales)', 'sum(Other_Sales)'
]).add_selection(sel).properties(width=800, height=500))
def comp_lapi_gest(df_passages_immat_ok,
donnees_gest,
camera,
date_d='2019-01-28',
date_f='2019-02-11'):
"""
Graph de comparaison entr eles donnes gestionnaire et les donnees lapi
en entree :
df_passages_immat_ok : df des passages valide cf donnees_postraitees.filtre_plaque_non_valable
donnees_gest : df des donnes gestionnaires, cf donnees_postraitees.donnees_gest
camera : entier : numero de camera
en sortie :
graph_comp_lapi_gest : chaetr altair de type bar
"""
# regrouper les données PL validées par jour et par camera
nb_pl_j_cam = df_passages_immat_ok.groupby('camera_id').resample(
'D').count()['immat'].reset_index().rename(columns={'immat': 'nb_veh'})
nb_pl_j_cam['type'] = 'lapi'
comp_traf_lapi_gest = pd.concat([nb_pl_j_cam, donnees_gest], sort=False)
comp_traf_lapi_gest_graph = comp_traf_lapi_gest.loc[
comp_traf_lapi_gest.created.between(pd.to_datetime(date_d),
pd.to_datetime(date_f))].copy()
return alt.Chart(comp_traf_lapi_gest_graph.loc[
comp_traf_lapi_gest_graph['camera_id'] == camera],
title=f'Camera {camera}').mark_bar(opacity=0.8).encode(
x=alt.X('monthdate(created):O',
axis=alt.Axis(title='date', labelAngle=80)),
y=alt.Y('nb_veh:Q',
stack=None,
axis=alt.Axis(title='Nombre de PL')),
color='type',
order=alt.Order(
"type", sort="ascending")).properties(width=500)
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 _parse_encoding_ecdf(encoding, complementary, sort):
"""Parse encoding for ECDF."""
if type(encoding) != dict:
raise RuntimeError('`encoding` must be specified as a dict.')
x, y, val = _make_xy_encoding_ecdf(encoding, complementary)
# Need to run through color spec twice to get cat
color = _make_color_encoding(encoding, None, sort)
if color == Undefined:
cat = None
else:
cat = _get_column_name(color)
color = _make_color_encoding(encoding, cat, sort)
# Build encoding for export
encoding = {
key: item
for key, item in encoding.items() if key not in ['x', 'y', 'color']
}
encoding['x'] = x
encoding['y'] = y
if cat is not None:
encoding['color'] = color
encoding['order'] = alt.Order(val + ':Q', sort='ascending')
return encoding, cat, val
def graph_TV_jo_cam_norm(df_pct_pl_transit,uvp,coeff_uvp, *cam):
"""
graph de synthese de la proportion de pl en transit, TV, PL Locaux par heure. Base nb pl dir et pct_pl_transit lapi
en entree :
df_pct_pl_transit : df du nb de vehicules, issus de resultat.pourcentage_pl_camera
uvp : booleen : si on veut le graph ne UVP ou non
coeff_uvp : float : coefficientd'equivalence PL- UVP. utilse si uvp=True, sinon eu importe mais doit exister
cam : integer : les cameras concernees
en sortie :
bar_nb_pl_dir_norm : chart altair avec la proportion de pl locaux, pl transit, tv
"""
concat_dir_trafic_normalisee=PL_transit_dir_jo_cam_normalise(df_pct_pl_transit,coeff_uvp, cam)
#creation du titre
if [voie for voie, cams in dico_corrsp_camera_site.items() if cams==list(cam)] :
titre=f'Proportion de vehicules sur {[voie for voie, cams in dico_corrsp_camera_site.items() if cams==list(cam)][0]}'
else :
if len(cam)>1 :
titre=f'Proportion de vehicules au droit des caméras {cam}'
else :
titre=f'Proportion de vehicules au droit de la caméra {cam[0]}'
bar_nb_pl_dir_norm=alt.Chart(concat_dir_trafic_normalisee, title=titre).mark_bar().encode(
x=alt.X('heure:O',axis=alt.Axis(title='Heure',titleFontSize=14,labelFontSize=14)),
y=alt.Y('nb_pl:Q',stack='normalize', axis=alt.Axis(title='Proportions de vehicules',titleFontSize=14,labelFontSize=14,format='%')),
color=alt.Color('type',sort=['PL locaux','PL en transit','Vehicules Legers'],legend=alt.Legend(title='Type de vehicules',titleFontSize=14,labelFontSize=14)),
order=alt.Order('type', sort='ascending')).properties(width=800, height=400).configure_title(fontSize=18)
return bar_nb_pl_dir_norm
def make_type_I_error_chart(results):
df = pd.DataFrame(results)
bars = alt.Chart(df).mark_bar(size=30).encode(
y=alt.Y('test:N',
title='Type of test',
axis=alt.Axis(titleFontSize=18, labelFontSize=15)),
x=alt.X('sum(error):Q',
title='Probability of Type I error',
axis=alt.Axis(titleFontSize=18, labelFontSize=15),
stack='zero'),
color=alt.Color('direction:N',
legend=alt.Legend(title=None,
labelFontSize=18,
labelLimit=1000)),
order=alt.Order('direction:N'),
tooltip=alt.Tooltip(['test', 'direction', 'error']))
# text = alt.Chart().mark_text(color='black', size=15, dx=-20).encode(
# y=alt.Y('test:N', title='Type of test',),
# x=alt.X('error:Q', title='Probability of Type I error', stack='zero'),
# text=alt.Text('error:Q', format='.3f'),
# order=alt.Order('direction:N'),
# tooltip=alt.Tooltip(['test', 'direction', 'error'])
# )
rule = alt.Chart(pd.DataFrame(
{'alpha': [.05]})).mark_rule(color='black').encode(x='alpha')
return alt.layer(bars, rule).properties(height=300, width=600)
def plot_top_users_time(user, types=['RT', 'Mention', 'Text', 'Reply', 'Quoted', 'Like'] ):
final = get_user_final_timeline(user, types)
all_users_x_month = alt.Chart(final,width=400).mark_bar(
cornerRadiusTopLeft=3,
cornerRadiusTopRight=3
).encode(
x='yearmonth(created_at):O',
y=alt.Y('count():Q'),#, sort=alt.SortField(field="count():Q", op="distinct", order='ascending')),
color=alt.Color('screen_name:N',sort='-y'),
order=alt.Order('count():Q')
)
outlier_transparency = alt.Chart(final, width=400).mark_bar(
cornerRadiusTopLeft=3,
cornerRadiusTopRight=3,
opacity=0.7,
color='black'
).encode(
x='yearmonth(created_at):O',
y=alt.Y('count():Q'),#, sort=alt.SortField(field="count():Q", op="distinct", order='ascending')),
opacity=alt.Opacity('outlier:O',sort='-y', scale=alt.Scale(range=[0.35,0])),
order='order:N'
).transform_calculate(
order="if (datum.outlier, 1, 0)"
)
return alt.layer(all_users_x_month,outlier_transparency).resolve_scale(color='independent')
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 make_bar_plot(category, damage):
"""
Generates a bar plot based on user selection of category and damage level
Parameters
----------
category - a string; user selected from dropdown and passed by callback
damage - a string; user selected from dropdown and passed by callback
Return
------
an altair plot converted to html
"""
alt.themes.register('mds_special', mds_special)
alt.themes.enable('mds_special')
#alt.themes.enable('none') # to return to default
query_string = ""
for user_select_damage in damage:
query_string += 'damage_level == "' + user_select_damage + '" | '
query_string = query_string[:-2]
x_title = category.replace('_', ' ').title()
main_title = 'Effect of ' + x_title + ' on Birdstrikes'
if len(query_string) != 0:
#generate a bar plot
bar_plot = alt.Chart(
df.query(query_string),
title=main_title).mark_bar(opacity=0.3).encode(
alt.X(category + ':O',
axis=alt.Axis(title=x_title, labelAngle=0),
sort=alt.EncodingSortField(field='damage_level_sort',
op='count',
order='ascending')),
alt.Y('count(damage_level):Q',
axis=alt.Axis(title="Bird Strikes"),
stack=True),
alt.Color(
'damage_level',
scale=alt.Scale(
domain=['Substantial', 'Medium', 'Minor', 'None'],
range=['red', 'dodgerblue', 'grey', 'darkgreen']),
legend=alt.Legend(orient='bottom',
titleOrient='left',
title="Damage Level",
labelFontSize=15,
titleFontSize=15)),
alt.Order('damage_level_sort', sort='ascending'),
alt.Tooltip(['count(damage_level)'])).properties(width=500,
height=400)
bar_plot = bar_plot.to_html()
else:
bar_plot = None
return bar_plot
def make_line_plot(date_list, damage):
query_string = ""
for user_select_damage in damage:
query_string += 'damage_level == "' + user_select_damage + '" | '
query_string = query_string[:-2]
df_line = df.query('year >= @date_list[0] & year <= @date_list[1]')
if len(query_string) != 0:
label = alt.selection_single(
encodings=['x'], # limit selection to x-axis value
on='mouseover', # select on mouseover events
nearest=True, # select data point nearest the cursor
empty='none' # empty selection includes no data points
)
line_plot_base = alt.Chart(
df_line.query(query_string), title='Bird Strike Damage over Time'
).mark_area(opacity=0.3, interpolate='monotone').encode(
alt.X('year:O', axis=alt.Axis(title="Year", labelAngle=0)),
alt.Y('count(damage_level):N',
axis=alt.Axis(title="Bird Strikes"),
stack=None),
alt.Color(
'damage_level',
#sort = ['Substantial', 'Medium', 'Minor', 'None'],
scale=alt.Scale(
domain=['Substantial', 'Medium', 'Minor', 'None'],
range=['red', 'dodgerblue', 'grey', 'darkgreen']),
legend=alt.Legend(title="Damage Level")),
#orient = 'none',
#legendX = 675, legendY = 10,
#fillColor = 'white')),
alt.Order('damage_level_sort', sort='ascending'))
line_plot = alt.layer(
line_plot_base,
alt.Chart().mark_rule(color='grey').encode(
x='year:O').transform_filter(label),
line_plot_base.mark_circle().encode(opacity=alt.condition(
label, alt.value(1), alt.value(0))).add_selection(label),
line_plot_base.mark_text(
align='left', dx=5, dy=-10, stroke='grey',
strokeWidth=1).encode(
text='count(damage_level):N').transform_filter(label),
line_plot_base.mark_text(align='left', dx=5, dy=-10).encode(
text='count(damage_level):N').transform_filter(label),
data=df).properties(width=650, height=400)
line_plot = line_plot.to_html()
else:
line_plot = None
return line_plot
def make_gdp_perc_chart(year=2018, stat_type='Export'):
'''
Create a bar chart that shows Imports/Exports (Dynamic based on switch/callback) as a percentage of GDP
in the year selected (based on year slider), and show the highest 15.
Parameters
-----------
year: integer [1988, 2018]
the year for which data is to be displayed - controlled by slider, default is 2018
stat_type: string one of 'Import' or 'Export'
determines whether this graph will show imports or exports as a percentage of GDP,
default is 'Export', and controlled by switch
Returns
-----------
gdp_perc_chart: chart
bar chart showing stat_type as a percentage of GDP for the specified year
Example
-----------
> make_gdp_perc_chart(2017, 'Import')
'''
countries = ['USA', 'Italy', 'Spain', 'Germany', 'Czech Rep.', 'Brazil', 'Norway',
'Switzerland', 'Turkey', 'Canada', 'Japan', 'Croatia', 'United Kingdom', 'France']
# Wrangling specific to this chart:
df_for_perc_of_gdp = arms_gdp[ # (arms_gdp['Country'].isin(countries)) &
(arms_gdp['Year'] == year) &
(arms_gdp['Direction'] == stat_type)].sort_values(by='percent_GDP', ascending=False).head(15)
# df_for_perc_of_gdp['percent_GDP'] = df_for_perc_of_gdp['percent_GDP'] * 100
# Make the chart:
gdp_perc_chart = alt.Chart(df_for_perc_of_gdp).mark_bar().encode(
alt.X('Country:N',
sort=alt.EncodingSortField(field='percent_GDP',
order='descending'),
title='Country',
axis=alt.Axis(labelAngle=45)),
alt.Y('percent_GDP:Q',
title='Arms Trade as a % of GDP',
# scale=alt.Scale(domain=(0, (0.2 if stat_type == 'Import' else 0.5)))
),
alt.Color('percent_GDP:Q', scale=alt.Scale(scheme='goldorange'), legend=None),
alt.Order(shorthand=['percent_GDP'], sort='descending'),
alt.Tooltip(['Country', 'percent_GDP'])
).configure_bar(color='orange'
).properties(width=920,
height=230,
background='white',
title="Arms Trade as a Percentage of GDP for Major " + stat_type + "ers in %d" % (
year))
return gdp_perc_chart
def stack_bar_chart():
rl_vio = doc(0)
#rl_vio["YEAR"] = rl_vio["YEAR"].astype("int")
source = rl_vio[rl_vio["YEAR"]>2014]
crash_type = ["FAILING TO REDUCE SPEED TO AVOID CRASH",
"FAILING TO YIELD RIGHT-OF-WAY",
"FOLLOWING TOO CLOSELY",
"IMPROPER LANE USAGE", "IMPROPER OVERTAKING/PASSING"]
st.sidebar.title("What causes the accidents?")
select1 = st.sidebar.selectbox("Choose the crash type: ", crash_type)
select2 = st.sidebar.selectbox("Choose the year: ", [2015,2016,2017,2018,2019,2020,2021])
st.text("Go back to see all types of causes? Click 'View All'!")
if st.button("View All"):
cha = alt.Chart(source).mark_bar(size=20).encode(
alt.Tooltip(["YEAR:O", "MONTH:O", "sum(RECORDS)"]),
alt.Y('YEAR:O', title="Year",axis=alt.Axis(grid=False, labelAngle=0)),
alt.X('sum(RECORDS)', axis=alt.Axis(grid=False, labelAngle=0), title="Records"),
color="CAUSE",
order=alt.Order(
# Sort the segments of the bars by this field
'CAUSE',
sort='ascending'
)).properties(
height=400,
width=850).transform_filter(
alt.FieldOneOfPredicate(field='CAUSE', oneOf=crash_type)
).interactive()
else:
if select1 in crash_type:
cha = alt.Chart(source).mark_bar(size=20).encode(
alt.Tooltip(["CAUSE:N", "sum(RECORDS)"]),
alt.Y('YEAR:O', axis=alt.Axis(grid=False, labelAngle=0), title="Year"),
alt.X('sum(RECORDS)', axis=alt.Axis(grid=False, labelAngle=0,tickMinStep = 1), title="Records"),
color=alt.value("#e7ba52")
).properties(
height=400,
width=600
).transform_filter(
alt.datum.CAUSE == select1
)
if select2:
cha = alt.Chart(source).mark_bar(size=20).encode(
alt.Tooltip(["YEAR:O", "MONTH:O", "sum(RECORDS)"]),
alt.Y('MONTH:O', axis=alt.Axis(grid=False, labelAngle=0), title="Month"),
alt.X('sum(RECORDS)', axis=alt.Axis(grid=False, labelAngle=0,tickMinStep = 1), title="Records"),
color=alt.value("darkgray")
).properties(
height=400,
width=600).transform_filter(
alt.datum.CAUSE == select1).transform_filter(alt.datum.YEAR == select2)
return cha
def plot_stacked_bars(df):
rnd = df.essrnd.iloc[0]
year = '2002' if rnd == 1 else '2014'
var = df.columns[1]
annot = questions[var]
return alt.Chart(df).mark_bar().encode(
alt.X(var, scale=alt.Scale(domain=[0, 1])),
y='cntry',
order=alt.Order('response', sort='ascending'),
color=alt.Color('response:O',
legend=alt.Legend(title='Response'),
scale=color_scale)).properties(
title=f"{annot[0]} * {year} * {annot[1]}")
def kaart_plot(cn6_x):
# Title
st.subheader("International trade flows to and from Europe in 2019")
x = pd.read_csv('data/edges_puhastus2019.csv', sep=';')
x = x.loc[:, ~x.columns.str.contains('^Unnamed')]
x = remap_cn6(x)
countries = pd.read_csv('countries.csv', sep=';')
world = alt.topo_feature(data.world_110m.url, 'countries')
x = x[x["cn6"] == cn6_x]
conns = x
select_country = alt.selection_single(on="mouseover",
nearest=True,
fields=["origin"],
empty="none")
lookup_data = alt.LookupData(countries,
key="country",
fields=["name", "latitude", "longitude"])
background = alt.Chart(world).mark_geoshape(
fill="lightgray",
stroke="white").properties(width=1000,
height=800).project(type='naturalEarth1')
connections = alt.Chart(conns).mark_rule(opacity=0.35).encode(
latitude="latitude:Q",
longitude="longitude:Q",
latitude2="lat2:Q",
longitude2="lon2:Q").transform_lookup(
lookup="origin", from_=lookup_data).transform_lookup(
lookup="destination",
from_=lookup_data,
as_=["country", "lat2",
"lon2"]).transform_filter(select_country)
points = alt.Chart(conns).mark_circle().encode(
latitude="latitude:Q",
longitude="longitude:Q",
size=alt.Size("connections:Q",
scale=alt.Scale(range=[0, 400]),
legend=None),
order=alt.Order("connections:Q", sort="descending"),
tooltip=["origin:N", "connections:Q"]).transform_aggregate(
connections="count()", groupby=["origin"]).transform_lookup(
lookup="origin",
from_=lookup_data).add_selection(select_country)
st.altair_chart((background + connections +
points).configure_view(stroke=None).resolve_scale())
# Description
st.markdown("""
International trade flows to and from EU in 2019. The size of the country node shows
the number of trade flows to and from other countries. Data:
[Comext](https://ec.europa.eu/eurostat/estat-navtree-portlet-prod/BulkDownloadListing?sort=1&dir=comext) yearly data.
""")
def plotClassOrder(self):
alt.data_transformers.disable_max_rows()
chart2 = alt.Chart(self.dataFrame).mark_bar().encode(
x=alt.X('sum(number)', type='quantitative', title='Total Number'),
y=alt.Y('clasS',
type='nominal',
title='Class',
sort=alt.SortField('number', order='descending')),
color='type',
order=alt.Order(
# Sort the segments of the bars by this field
'type',
sort='ascending'))
chart2.display()
def make_chart_topic_trends(
topic_trends, arxiv_cat_lookup, year_sort=2020, save=True, fig_n=4
):
"""Topic trend chart"""
# Sort topics by the year of interest
topics_sorted = (
topic_trends.loc[[x.year == year_sort for x in topic_trends["date"]]]
.groupby("topic_cat")["value"]
.sum()
.sort_values(ascending=False)
.index.tolist()
)
topic_trends["order"] = [
[n for n, k in enumerate(topics_sorted) if x == k][0]
for x in topic_trends["topic_cat"]
]
# Create clean category names
topic_trends["topic_cat_clean"] = [
arxiv_cat_lookup[x][:50] + "..." for x in topic_trends["topic_cat"]
]
# Create clean topic sorted names
topics_sorted_2 = [arxiv_cat_lookup[x][:50] + "..." for x in topics_sorted]
evol_sh = (
alt.Chart(topic_trends)
.mark_bar(stroke="grey", strokeWidth=0.1)
.encode(
x="date:T",
y=alt.Y("value", scale=alt.Scale(domain=[0, 1])),
color=alt.Color(
"topic_cat_clean",
sort=topics_sorted_2,
title="Source category",
scale=alt.Scale(scheme="tableau20"),
legend=alt.Legend(columns=2),
),
order=alt.Order("order", sort="descending"),
tooltip=["topic_cat_clean"],
)
).properties(width=400)
if save is True:
save_altair(evol_sh, f"fig_{fig_n}_topic_trends", driv)
return evol_sh
def graph_TV_jo_cam(df_pct_pl_transit,uvp,coeff_uvp, *cam):
"""
graph de synthese du nombre de pl en trasit, TV et pl totaux par heure. Base nb pl dir et pct_pl_transit lapi
en entree :
df_pct_pl_transit : df du nb de vehicules, issus de resultat.pourcentage_pl_camera
uvp : booleen : si on veut le graph ne UVP ou non
coeff_uvp : float : coefficientd'equivalence PL- UVP. utilse si uvp=True, sinon eu importe mais doit exister
cam : integer : les cameras concernees
en sortie :
bar_nb_pl_dir : chart altair avec le nb pl, nb pl transit, tv
"""
concat_dir_trafic=PL_transit_dir_jo_cam(df_pct_pl_transit,coeff_uvp, cam)[0]
#creation du titre
if [voie for voie, cams in dico_corrsp_camera_site.items() if cams==list(cam)] :
titre=f'Nombre de véhicules sur {[voie for voie, cams in dico_corrsp_camera_site.items() if cams==list(cam)][0]}'
else :
if len(cam)>1 :
titre=f'Nombre de véhicules au droit des caméras {cam}'
else :
titre=f'Nombre de véhicules au droit de la caméra {cam[0]}'
if not uvp :
concat_dir_trafic=concat_dir_trafic.loc[concat_dir_trafic.type.isin(['Tous PL','PL en transit','Tous Vehicules'])].copy()
bar_nb_pl_dir=alt.Chart(concat_dir_trafic, title=titre).mark_bar().encode(
x=alt.X('heure:O',axis=alt.Axis(title='Heure',titleFontSize=14,labelFontSize=14)),
y=alt.Y('nb_pl:Q',stack=None, axis=alt.Axis(title='Nombre de vehicules',titleFontSize=14,labelFontSize=14)),
color=alt.Color('type',sort=['Tous vehicules', 'Tous PL','PL en transit'],legend=alt.Legend(title='Type de vehicules',titleFontSize=14,labelFontSize=14)),
order=alt.Order('type', sort='descending')).properties(width=800, height=400).configure_title(fontSize=18)
else :
concat_dir_trafic=concat_dir_trafic.loc[concat_dir_trafic.type.isin(['UVP Tous PL','UVP PL en transit','UVP Tous Vehicules'])].copy()
bar_nb_pl_dir=alt.Chart(concat_dir_trafic, title=titre).mark_bar().encode(
x=alt.X('heure:O',axis=alt.Axis(title='Heure',titleFontSize=14,labelFontSize=14)),
y=alt.Y('nb_pl:Q',stack=None, axis=alt.Axis(title='Nombre de vehicules',titleFontSize=14,labelFontSize=14)),
color=alt.Color('type',sort=['UVP Tous vehicules', 'UVP Tous PL','UVP PL en transit'],legend=alt.Legend(title='Type de vehicules',titleFontSize=14,labelFontSize=14)),
order=alt.Order('type', sort='descending')).properties(width=800, height=400).configure_title(fontSize=18)
return bar_nb_pl_dir
def plot_kanban(self,
tasks: List[Task],
sort: List[str] = None,
group: str = None) -> None:
logging.info(f"ALTAIR KANBAN PLOT. TASKS #: {len(tasks)}")
group = group or 'state'
detail = 'owner' if group == 'state' else 'state'
task_dict_list = [{
'weight': 1,
**vars(task)
} for task in tasks if not task.summary]
counts = Counter(task_dict[group]
for task_dict in task_dict_list).most_common()
_, max_depth = next(iter(counts))
source = pd.DataFrame(task_dict_list)
title = f"Kanban Chart | {date.today()}"
block_height = 50
block_width = block_height * 8
base = alt.Chart(source).mark_bar(color='black').encode(
x=alt.X(group,
axis=alt.Axis(orient='top', labelAngle=0,
labelFontSize=15),
sort=sort),
y=alt.Y('sum(weight)', sort='descending', stack='zero'),
order=alt.Order('id', sort='ascending')).properties(
title=title,
width=block_width * len(counts),
height=block_height * max_depth)
bars = base.encode(color=alt.Color('id:N', legend=None))
text = base.mark_text(dy=-(block_height * 0.33),
color='black').encode(text='name')
info = base.mark_text(dy=-(block_height * 0.67),
dx=(block_width * 0.3),
color='#2F4F4F').encode(text=detail)
chart = bars + text + info
output_file = str(Path(self.plot_dir).joinpath('kanban.html'))
chart.save(output_file)
def plot_components(df, placeholder):
df = df.melt(id_vars='Timestamp',
var_name='Components',
value_name='Power')
c = alt.Chart(df).transform_joinaggregate(
order='sum(Power)', groupby=['Components']).mark_area().encode(
x='Timestamp:T',
y='Power:Q',
color=alt.Color('Components:N',
legend=alt.Legend(orient="bottom")),
order=alt.Order('order:Q', sort='descending'),
tooltip=['Components', 'hoursminutes(Timestamp)', 'Power'])
placeholder.altair_chart(c, use_container_width=True)
return placeholder
def createStackPlot(df):
return alt.Chart(df).mark_bar().encode(
x=alt.X('Segundos:Q', axis=alt.Axis(title=None)), #hoursminutes(
y=alt.Y('Name:N',
axis=alt.Axis(grid=False, title=None),
sort=alt.EncodingSortField(field="Segundos",
op="sum",
order='ascending')),
color=alt.Color(
'Classe:N',
sort=['SwimN', 'T1N', 'BikeN', 'T2N', 'RunN'],
scale=alt.Scale(scheme='tableau20')
), #scale=alt.Scale(range=['#96ceb4', '#BF820E','#4BA55E', '#4FA7A5', '#CBBE00'])
tooltip=['Tempo:N'],
order=alt.Order('Order', sort='ascending')).configure_view(
strokeOpacity=0).properties(height=400, width=900)
def plot_play_count_graph(info_content_df: pd.DataFrame):
chart = alt.Chart(info_content_df).mark_bar().encode(
x='count()',
y='learning_stage',
color='difficulty',
order=alt.Order(
# Sort the segments of the bars by this field
'learning_stage',
sort='ascending'
)
).properties(
width=1500,
height=200
)
return chart
def percapita_trend(highlight, highlight2):
total = alt.Chart(df).mark_bar().encode(
alt.X('Year:N', title="Year"),
alt.Y('CO2 emissions per capita',
title='CO2 emissions per capita (kt)'),
color=alt.Color('Country Name',
scale=alt.Scale(scheme="set3"),
title='Countries'),
order=alt.Order(
# Sort the segments of the bars by this field
'CO2 emissions per capita',
sort='ascending'),
tooltip=["Country Name", 'CO2 emissions per capita']).properties(
width=530,
height=350,
title='CO2 emissions per capita world trend').transform_filter(
highlight | highlight2)
return total
