def make_charts(df, color, x_axis_title, y_axis_title, title):
chart = Chart(data=df, height=height,
width=width).mark_bar(color=color).encode(
X('name', axis=Axis(title=x_axis_title), sort=None),
Y('data',
axis=Axis(title=y_axis_title))).properties(title=title)
return chart.to_json()
def data_bar_jail():
county_data = read_county_from_db(session.get('current_state'),
session.get('current_county'))
# Create the chart
jail = Chart(data=county_data, height=HEIGHT,
width=WIDTH).mark_bar(color='#444760').encode(
X('year:O', axis=Axis(title='Year')),
Y('total_jail_pop',
axis=Axis(title='Total Jail Population')),
tooltip=[
alt.Tooltip('year', title='Year'),
alt.Tooltip('total_jail_pop',
title='Total jail population')
]).properties(title='Jail population in {}'.format(
session.get('current_county'))).interactive()
# Create pre-trial chart to overlay on top
pre_trial = Chart(data=county_data, height=HEIGHT, width=WIDTH).mark_bar(
color="#d66241",
interpolate='step-after',
line=True,
).encode(X('year:O', axis=Axis(title='Year')),
Y('total_jail_pretrial', axis=Axis(title='Number of inmates')),
tooltip=[
alt.Tooltip('year', title='Year'),
alt.Tooltip('total_jail_pretrial',
title='Pre-trial jail population')
]).properties(title='Pre-trial jail population in {}'.format(
session.get('current_county'))).interactive()
chart = alt.layer(jail + pre_trial)
return chart.to_json()
def data_bar_jail():
county_data = read_county_from_db(session.get(
'current_state'), session.get('current_county'))
# Create a label for the jail population to be included in the chart.
# Result of lambda is a float, thus the slice notation is used
county_data['total_jail_pop_label'] = county_data['total_jail_pop'].apply(lambda x: "{:,}".format(x)[:-2])
county_data['total_jail_pretrial_label'] = county_data['total_jail_pretrial'].apply(lambda x: "{:,}".format(x)[:-2])
# Create the chart
jail = Chart(data=county_data, height=HEIGHT, width=WIDTH).mark_bar(color='#444760').encode(
X('year:O', axis=Axis(title='Year')),
Y('total_jail_pop', axis=Axis(title='Total Jail Population')),
tooltip=[alt.Tooltip('year', title='Year'), alt.Tooltip(
'total_jail_pop_label', title='Total jail population')]
).properties(
title='Jail population in {}'.format(session.get('current_county'))
).interactive()
# Create pre-trial chart to overlay on top
pre_trial = Chart(data=county_data, height=HEIGHT, width=WIDTH).mark_bar(
color="#d66241", interpolate='step-after', line=True,
).encode(
X('year:O', axis=Axis(title='Year')),
Y('total_jail_pretrial', axis=Axis(title='Number of inmates')),
tooltip=[alt.Tooltip('year', title='Year'), alt.Tooltip(
'total_jail_pretrial_label', title='Pre-trial jail population')]
).properties(
title='Pre-trial jail population in {}'.format(
session.get('current_county'))
).interactive()
chart = alt.layer(jail + pre_trial)
return chart.to_json()
def data_line():
chart = (Chart(data=sample_data.df_list, height=HEIGHT,
width=WIDTH).mark_line(color="green").encode(
X("name", axis=Axis(title="Sample")),
Y("data", axis=Axis(title="Value")),
).interactive())
return chart.to_json()
def county_scatter():
state_name = session.get('current_state')
county_name = session.get('current_county')
# Connect to the database
conn = sqlite3.connect('./db/incarceration.db')
# Determine whether 2015 or 2016 has more data
year_2016_nulls = test_nulls_for_year(2016, state_name, conn)
year_2015_nulls = test_nulls_for_year(2015, state_name, conn)
year = 2016 # default year
# Test to see if 2015 has more non-null values
if year_2016_nulls.iloc[0]['PercentNotNull'] < year_2015_nulls.iloc[0]['PercentNotNull']:
year = 2015
# Select prison population data for the entire state for the selected year
all_counties_prison_pop = pd.read_sql_query(f"""SELECT county_name, total_pop, total_prison_pop, urbanicity
FROM
incarceration
WHERE state = '{state_name}'
AND year = {year};
""", conn)
# Select prison population data for the specific county for the selected year
county_prison_pop = pd.read_sql_query(f"""SELECT county_name, total_pop, total_prison_pop, urbanicity
FROM
incarceration
WHERE state = '{state_name}'
AND county_name = '{county_name}'
AND year = {year};
""", conn)
# Close connection
conn.close()
state_chart = Chart(data=all_counties_prison_pop, height=HEIGHT, width=WIDTH).mark_circle(size=70).encode(
X('total_pop', axis=Axis(title='County population')),
Y('total_prison_pop', axis=Axis(title='Total prison population')),
color=alt.Color('urbanicity', legend=alt.Legend(title='Urbanicity')),
size=alt.Color('total_pop', legend=alt.Legend(
title='Total population')),
tooltip=[alt.Tooltip('county_name', title='County'), alt.Tooltip(
'total_pop', title='Total county population'), alt.Tooltip('total_prison_pop', title='Total prison population')],
).properties(
title='Statewide prison population {}, {}'.format(year, state_name)).interactive()
county_chart=Chart(data=county_prison_pop, height=HEIGHT, width=WIDTH).mark_square(
size=250, fillOpacity=0.5, stroke='black', color='black').encode(
X('total_pop', axis=Axis(title='County population')),
Y('total_prison_pop', axis=Axis(title='Total prison population')),
tooltip=['county_name', 'total_pop', 'total_prison_pop']
).interactive()
chart=alt.layer(county_chart, state_chart)
return chart.to_json()
def data_waterfall():
chart = (Chart(
data=sample_data.df_water,
width=WIDTH,
).mark_bar(color="gray").encode(
X("Name", axis=Axis(title="Sample")),
Y("Value", axis=Axis(title="Value")),
).interactive())
return chart.to_json()
def gen_var_barcharts_by_geo(data, var, agg_type, geo):
data = aggregate_data(data, agg_type, geo)
titlex = agg_type + ' of ' + var.split('_', 1)[1].replace('_', ' ')
titley = geo.replace('_', ' ')
bar_chart = alt.Chart(data).mark_bar().encode(x=X(var,
axis=Axis(title=titlex)),
y=Y((geo + ':O'),
axis=Axis(title=titley)))
with open('./runs/%s_by_%s.json' % (var, geo), 'w') as outfile:
json.dump(bar_chart.to_json(), outfile)
def gen_custom_barchart(table, var):
df = orca.get_table(table).to_frame(['parcel_id', var]).\
groupby(var).count().reset_index()
df.rename(columns={'parcel_id': 'count_' + table}, inplace=True)
chart = alt.Chart(df).mark_bar().encode(x=X('count_' + table,
axis=Axis(title='count_' +
table)),
y=Y(var + ':O',
axis=Axis(title=var)))
with open('./runs/%s_by_%s.json' % (table, var), 'w') as outfile:
json.dump(chart.to_json(), outfile)
def gen_barcharts_n_largest(data, var, agg_type, geo, n):
data = aggregate_data(data, agg_type, geo)
max_data = data.nlargest(n, var).reset_index()
titlex = agg_type + ' of ' + var.split('_', 1)[1].replace('_', ' ')
titley = geo.replace('_', ' ')
bar_chart = alt.Chart(max_data).mark_bar().encode(
x=X(var, axis=Axis(title=titlex)),
y=Y(geo + ':O', axis=Axis(title=titley)))
with open('./runs/%s_%ss_with_max_%s.json' % (n, geo, var),
'w') as outfile:
json.dump(bar_chart.to_json(), outfile)
def data_bar_prison():
county_data = read_county_from_db(session.get('current_state'),
session.get('current_county'))
# Create the chart
chart = Chart(
data=county_data, height=HEIGHT,
width=WIDTH).mark_bar(color='#2f3142').encode(
X('year:O', axis=Axis(title='Year')),
Y('total_prison_pop',
axis=Axis(title='Total Prison Population'))).properties(
title='Prison population in {}'.format(
session.get('current_county')))
return chart.to_json()
def pretrial_jail_chart():
county_data = read_county_from_db(session.get('current_state'),
session.get('current_county'))
chart = Chart(data=county_data, height=HEIGHT, width=WIDTH).mark_line(
color="#08080B",
interpolate='step-after',
line=True,
).encode(X('year:O', axis=Axis(title='Year')),
Y('total_jail_pretrial', axis=Axis(title='Number of inmates')),
tooltip=[
'year', 'total_jail_pretrial'
]).properties(title='Pre-trial jail population in {}'.format(
session.get('current_county'))).interactive()
return chart.to_json()
def create_bins(data):
columns = ['Wind Speed (kts)', 'Rain (mm)', 'Temp (◦C)', 'Humidity (%)']
filenumber = 1
for items in columns:
means = data.groupby(['Location'])[items].mean()
means = means.to_frame()
bins = pd.cut(means[items], 3, labels=['Low', 'Moderate', 'High'])
bins = bins.to_frame()
bracket = items.index('(')
legend = items[:bracket]
bins.columns.values[0] = 'Average ' + legend + 'Category '
means.columns.values[0] = 'Average ' + items + ' Per Station'
new_df = pd.concat([means, bins], axis=1, join_axes=[means.index])
new_df.reset_index(level=0, inplace=True)
new_df
graph = alt.Chart(new_df).mark_bar().encode(
x='Location',
y=Y(means.columns.values[0], axis=Axis(format='f')),
#https://github.com/altair-viz/altair/issues/191
color=bins.columns.values[0])
filename = 'templates/plot' + str(filenumber) + '.html'
graph.savechart(filename)
filenumber += 1
def gen_var_histograms(data, var, agg_type, geo, vdict, cdict):
data = aggregate_data(data, agg_type, geo)
data = data.copy()
type = vdict[var].split(' ')[0]
if type == 'Log':
log_var = var
data[log_var] = data[var]
else:
log_var = 'log_' + var
data[log_var] = np.log(data[var])
titlex = 'log of ' + var.split('_', 1)[1].replace('_', ' ')
titley = 'number of ' + geo.replace('_', ' ') + 's'
hist = alt.Chart(data).mark_bar().encode(
alt.X(log_var, bin=True, axis=Axis(title=titlex)),
alt.Y('count()', axis=Axis(title=titley)))
with open('./runs/%s_histogram.json' % var, 'w') as outfile:
json.dump(hist.to_json(), outfile)
def gen_var_scatters(data, var1, var2, agg1, agg2, geo_points, geo_large):
colors = data.groupby(geo_points).min().reset_index()
colors = colors[[geo_points, geo_large]]
data_1 = aggregate_data(data, agg1, geo_points)[[var1, geo_points]]
data_2 = aggregate_data(data, agg2, geo_points)[[var2, geo_points]]
data = pd.merge(data_1, data_2, on=geo_points, how='left')
data = pd.merge(data, colors, on=geo_points, how='left')
titlex = agg1 + ' of ' + var1.split('_', 1)[1].replace('_',
' ') + ' by zone'
titley = agg2 + ' of ' + var2.split('_', 1)[1].replace('_',
' ') + ' by zone'
scatter = alt.Chart(data).mark_point().encode(
x=X(var1, axis=Axis(title=titlex)),
y=Y(var2, axis=Axis(title=titley)),
color=geo_large + ':N',
)
with open('./runs/%s_vs_%s.json' % (var2, var1), 'w') as outfile:
json.dump(scatter.to_json(), outfile)
def data_bar_prison():
county_data = read_county_from_db(session.get(
'current_state'), session.get('current_county'))
# Create a label for the prison population to be included in the chart.
# Result of lambda is a float, thus the slice notation is used
county_data['total_prison_pop_label'] = county_data['total_prison_pop'].apply(lambda x: "{:,}".format(x)[:-2])
# Create the chart
chart = Chart(data=county_data, height=HEIGHT, width=WIDTH).mark_bar(color='#2f3142').encode(
X('year:O', axis=Axis(title='Year')),
Y('total_prison_pop', axis=Axis(title='Total Prison Population')),
tooltip=[alt.Tooltip('year', title='Year'), alt.Tooltip(
'total_prison_pop_label', title='Total prison population')]
).properties(
title='Prison population in {}'.format(session.get('current_county'))
).interactive()
return chart.to_json()
def _encode_fields(self,
xfield,
yfield,
time_unit=None,
scale=Scale(zero=False)):
"""
Encode the fields in Altair format
"""
if scale is None:
scale = Scale()
xfieldtype = xfield[1]
yfieldtype = yfield[1]
x_options = None
if len(xfield) > 2:
x_options = xfield[2]
y_options = None
if len(yfield) > 2:
y_options = yfield[2]
if time_unit is not None:
if x_options is None:
xencode = X(xfieldtype, timeUnit=time_unit)
else:
xencode = X(xfieldtype,
axis=Axis(**x_options),
timeUnit=time_unit,
scale=scale)
else:
if x_options is None:
xencode = X(xfieldtype)
else:
xencode = X(xfieldtype, axis=Axis(**x_options), scale=scale)
if y_options is None:
yencode = Y(yfieldtype, scale=scale)
else:
yencode = Y(yfieldtype, axis=Axis(**y_options), scale=scale)
return xencode, yencode
def color_heatmap(data,
row,
column,
column_to_color,
colormap_domain,
colormap_range,
cellsize=(10, 10)):
"""Create an Altair/vega-lite Heat-Map with colormap parameter
Parameters
----------
data : dataframe to display, or url of csv file
row, column, color, column_to_color : str
Altair trait shorthands
colormap_domain : list of strings - html color names, or hex value strings
colormap_range : list of normalized values binned to colormap_domain
cellsize : tuple
specify (width, height) of cells in pixels
"""
return Chart(data).mark_text(applyColorToBackground=True, ).encode(
color=Color(
column_to_color,
legend=Legend(
orient='right',
title=column_to_color,
# # visible values in legend labels:
# # in order to avoid blob of legend labels
# # display only the max and min of values in given domain
values=[colormap_domain[0], colormap_domain[-1]],
labelAlign='left',
),
scale=Scale(domain=colormap_domain, range=colormap_range),
),
column=Column(
column,
axis=Axis(
labelAngle=270.0,
orient='bottom',
title=column,
),
),
row=row,
text=Text(value=' ', ),
).configure_scale(textBandWidth=cellsize[0], bandSize=cellsize[1])
def data_waterfall():
chart = Chart(data.df_water).mark_bar(color='lightgreen').encode(
X('Name', axis=Axis(title='Sample')),
Y('Value', axis=Axis(title='Value')))
return chart.to_json()
def data_bar():
chart = Chart(data=sample_data.df_list, height=HEIGHT,
width=WIDTH).mark_bar(color='yellow').encode(
X('name', axis=Axis(title='Sample')),
Y('data', axis=Axis(title='Value'))).interactive()
return chart.to_json()
def data_waterfall():
chart = Chart(sample_data.df_water).mark_bar(color='gray').encode(
X('Name', axis=Axis(title='Sample')),
Y('Value', axis=Axis(title='Value'))).interactive()
return chart.to_json()
data['temp'] = data['temp'].apply(f)
json_filename = sys.argv[2] + '.json'
csv_filename = sys.argv[2] + '.csv'
data.to_json(path_or_buf=json_filename, orient='records', date_format='iso')
#data.to_csv(path_or_buf=csv_filename)
colors = [
"#67001f", "#b2182b", "#d6604d", "#f4a582", "#fddbc7", "#d1e5f0",
"#92c5de", "#4393c3", "#2166ac", "#053061"
]
colors = colors[::-1]
#d = [0, 12, 24, 36, 48, 60, 72, 84, 96, 108]
d = [0, 120]
r = Row('dt:T', timeUnit='hours', axis=Axis(title='Hour of day'))
c = Column('dt:T',
timeUnit='monthdate',
axis=Axis(format=u'%b', labels=False, title='Month'))
col = Color(
'temp:N',
bin=Bin(step=12),
scale=Scale(domain=[0, 120], range=colors, clamp=True, zero=True),
#scale=Scale(range=colors, domain=[0, 120], zero=True),
legend=Legend(title="Temperature", format=u'.0f'))
chart = Chart(data).mark_text(applyColorToBackground=True).encode(
row=r, column=c, text=Text('blanks'),
color=col).configure_scale(textBandWidth=3, bandSize=25)
chart.max_rows = 8761
def multiline():
county_data = read_county_from_db(session.get(
'current_state'), session.get('current_county'))
source = helper_functions.process_data(county_data)
# Create a column for the label
source['value_label'] = source['value'].apply(lambda x: helper_functions.round_non_null_nums(x))
# Create a selection that chooses the nearest point & selects based on x-value
nearest = alt.selection(type='single', nearest=True, on='mouseover',
fields=['year'], empty='none')
demographics = ['Total white population (15-64)',
'Total black population (15-64)',
'White jail population',
'Black jail population',
'White prison population',
'Black prison population']
# Define color pairs matched to above demographics
hex_colors = ['#cccec1',
'#272727',
'#cccec1',
'#272727',
'#cccec1',
'#272727']
# Combine demographic and colors into a dictionary
demographic_labels = dict(zip(demographics, hex_colors))
# Create pairs of variables to be used in the stacked charts
wb_general = ['perc_white_total_pop', 'perc_black_total_pop']
wb_jail = ['perc_white_jail_pop', 'perc_black_jail_pop']
wb_prison = ['perc_white_prison_pop', 'perc_black_prison_pop']
# General population chart
total_wb_population = alt.Chart(source[source['variable'].isin(wb_general)], height=150, width=500).mark_bar().encode(
x=alt.X("year:O", axis=Axis(title='Year')),
y=alt.Y("value:Q", stack="normalize", axis=Axis(title='Ratio')),
color=alt.Color('demographic:N', legend=None,
scale=alt.Scale(domain=list(demographic_labels.keys()),
range=list(demographic_labels.values())
)
)
).properties(
title='Ratio of white/black residents in total county population (15-64)'
)
if session.get('jail_data_exists'):
# White/black jail population chart
total_wb_jail = alt.Chart(source[source['variable'].isin(wb_jail)], height=150, width=500).mark_bar().encode(
x=alt.X("year:O", axis=Axis(title='Year')),
y=alt.Y("value:Q", stack="normalize", axis=Axis(title='Ratio')),
color=alt.Color('demographic:N', legend=None,
scale=alt.Scale(domain=list(demographic_labels.keys()),
range=list(demographic_labels.values())
)
)
).properties(
title='Ratio of white/black inmates in jail population'
)
if session.get('prison_data_exists'):
total_wb_prison = alt.Chart(source[source['variable'].isin(wb_prison)], height=150, width=500).mark_bar().encode(
x=alt.X("year:O", axis=Axis(title='Year')),
y=alt.Y("value:Q", stack="normalize", axis=Axis(title='Ratio')),
color=alt.Color('demographic:N', legend=None,
scale=alt.Scale(domain=list(demographic_labels.keys()),
range=list(demographic_labels.values())
)
)
).properties(
title='Ratio of white/black inmates in prison population'
)
# Concatenate charts depending on what data is available
if session.get('prison_data_exists') and session.get('jail_data_exists'):
chart = alt.vconcat(total_wb_population, total_wb_jail, total_wb_prison)
elif session.get('prison_data_exists') and not session.get('jail_data_exists'):
chart = alt.vconcat(total_wb_population, total_wb_prison)
elif not session.get('prison_data_exists') and session.get('jail_data_exists'):
chart = alt.vconcat(total_wb_population, total_wb_jail)
else:
chart = total_wb_population
return chart.to_json()
import pandas as pd
import numpy as np
from altair import Chart, X, Y, SortField, Detail, Axis
csv_path = "../data/dropped-frames.csv"
df = pd.read_csv(csv_path, parse_dates=["Dropped Frame Start", "Dropped Frame End"], low_memory=False)
data = df[['Officer ID', 'Dropped Frame Start', 'Duration', 'FPS', 'Dropped Frames', 'Resolution', 'File Size', 'File Name', 'Frame Range', 'Player Time Range']]
data = data.rename(columns={'Dropped Frame Start': 'Timestamp'})
## Overview
Chart(data.sample(100)).configure_axis(gridColor='#ccc').mark_line(interpolate='linear').encode(
X(field='Timestamp', type='temporal', timeUnit='yearmonth', axis=Axis(title=' ', ticks=6, labelAngle=0, tickSizeEnd=0, tickSize=0, tickPadding=10)),
Y('sum(Duration)', axis=Axis(title='Seconds lost'))
).savechart('test.svg')
x_vals = range(0, 1000)
y_vals = []
for price in day_change:
y_vals.append(price)
data = Data(X=x_vals, Y=y_vals)
chart = Chart(data)
mark = chart.mark_point()
enc = mark.encode(x='X', y='Y')
enc.display()
data = Data(change=day_change)
chart = Chart(data)
mark = chart.mark_bar()
X = Axis('change:Q', bin=True)
Y = Axis('count()')
enc = mark.encode(x=X, y=Y)
enc.display()
print(mean(day_change))
print(stdev(day_change))
# predictions
# print(lines2[999][4])
# 306.730011
change = 0
change_guess = []
start_price = 306.730011
worst = 0
def data_line():
chart = Chart(data=data.df_list, height=HEIGHT,
width=WIDTH).mark_line().encode(
X('name', axis=Axis(title='Sample')),
Y('data', axis=Axis(title='Value')))
return chart.to_json()
def chartLog():
"Display chart for selected log"
db_folder = app.config['UPLOAD_FOLDER']
logFiles = glob.glob('%s/*.db' % db_folder)
form = ChartLog()
form.logFile.choices = [(f, f) for f in logFiles]
form.chartId.choices = [(q['id'], q['id']) for q in queries.graphs]
try:
dbname = app.dbname
if os.path.exists(dbname):
form.logFile.data = dbname
except:
pass
if not form.validate_on_submit():
return render_template('chartLog.html',
chart={},
dbName=None,
form=form)
dbname = os.path.join(form.logFile.data)
if not os.path.exists(dbname):
flash('Database does not exist', 'error')
return render_template('error.html', title='Database error')
try:
conn = sqlite3.connect(dbname)
except Exception as e:
app.logger.error(traceback.format_exc())
flash('Error: %s' % (str(e)), 'error')
return render_template('error.html',
title='Error in database reporting')
chartId = form.chartId.data
charts = [q for q in queries.graphs if q['id'] == chartId]
if not charts:
flash("Error: logic error couldn't find chartId", 'error')
return render_template(
'error.html', title='Error in in configuration of chart reports')
q = charts[0]
app.logger.debug("running chart query: %s - %s" % (q['title'], q['sql']))
start = datetime.now()
try:
df = pd.read_sql_query(q['sql'], conn)
except Exception as e:
flash('Error: %s' % (str(e)), 'error')
return render_template('error.html',
title='Error in database reporting')
end = datetime.now()
delta = end - start
if q['graph_type'] == 'line':
chart = Chart(data=df, height=HEIGHT, width=WIDTH).mark_line().encode(
X(q['x']['field'],
axis=Axis(title=q['x']['title'], labelOverlap='greedy')),
Y(q['y']['field'], axis=Axis(title=q['y']['title'])))
else:
chart = Chart(data=df, height=HEIGHT, width=WIDTH).mark_bar().encode(
X(q['x']['field'],
axis=Axis(title=q['x']['title'], labelOverlap='greedy')),
Y(q['y']['field'], axis=Axis(title=q['y']['title'])))
data = {
'id': "chart",
'data': chart.to_json(),
'title': q['title'],
'explanation': q['explanation'],
'sql': q['sql'],
'time_taken': str(delta)
}
return render_template('chartLog.html',
chart=data,
dbName=dbname,
form=form)
result['Time'] = result.apply(lambda row: news(row) , axis=1)
df_dados = result.loc[:][['Rodada','Temporada','Time','Resultado']].copy()
df_dados.sort_values(by=['Rodada'] ,ascending=True , inplace=True)
df_dados['Acumulado'] = df_dados.groupby(['Temporada','Time'])[['Time','Resultado']].cumsum()
x = st.slider('Selecione o ano',2012, 2019, (2012))
df_dados = df_dados[df_dados['Temporada'] == x].reset_index(drop=True)
st.dataframe(df_dados)
bars = alt.Chart(df_dados).mark_bar().encode(
x=X('2:Q',axis=Axis(title='Brasileirao')),
y=Y('0:Q',axis=Axis(title='Times'))
).properties(
width=650,
height=400
)
bar_plot = st.altair_chart(bars)
def plot_bar_animated_altair(df,week):
bars = alt.Chart(df, title="Ranking por Rodada :"+week)
for week in range(1,39):
teste = str(week)
bars = plot_bar_animated_altair(df_dados[df_dados['Rodada']== teste],teste)
time.sleep(0.01)