janbenetka

colors = ['aliceblue', 'antiquewhite', 'aqua', 'aquamarine', 'azure',
'beige', 'bisque', 'black', 'blanchedalmond', 'blue',
'blueviolet', 'brown', 'burlywood', 'cadetblue',
'chartreuse', 'chocolate', 'coral', 'cornflowerblue',
'cornsilk', 'crimson', 'cyan', 'darkblue', 'darkcyan',
'darkgoldenrod', 'darkgray', 'darkgrey', 'darkgreen',
'darkkhaki', 'darkmagenta', 'darkolivegreen', 'darkorange',
'darkorchid', 'darkred', 'darksalmon', 'darkseagreen',
'darkslateblue', 'darkslategray', 'darkslategrey',
'darkturquoise', 'darkviolet', 'deeppink', 'deepskyblue',

janbenetka

df.query('a in ["a", "b", "c"]')


id_list = ["a", "b", "c"]
df.query('a in @id_list')

janbenetka

SUBSTR(FORMAT("00%d", state_fips ), -2) as state_fips,
SUBSTR(FORMAT("00000%d", fips ), -5) as fips,

janbenetka

ARRAY_TO_STRING(homeContext.fipscode, ',')

janbenetka

from cartoframes.viz import Map, Layer, basemaps
from cartoframes.viz import Layer, color_continuous_style, color_bins_style, basic_style, color_category_legend


_df = average_duration.copy()
metric = 'avg_duration_day'

origin_county = selected_area_geom.iloc[0]['county_name']
origin_state = selected_area_geom.iloc[0]['state_name']

janbenetka

slack_message = "Home & Work for bundleId {} is ready for shipping!".format("{{ ti.xcom_pull(task_ids='get_bundle_id') }}")
notify_slack = SimpleHttpOperator(
    task_id="notify_slack",
    endpoint=slack_webhook_url,
    data=json.dumps(
        {"attachments": [{"fallback": slack_message, "text": slack_message, "color": "good"}]}),
    headers={"Content-Type": "application/json"},
    depends_on_past=False,
    response_check=lambda response: True if response.status_code == 200 else False,
    http_conn_id="http_slack_hook"

janbenetka

!pip install plotly==4.8

# Quick way to install hind font
!npm install -g google-font-installer
!gfi install hind -v 300

import plotly.graph_objs as go
import plotly.io as pio

pd.options.plotting.backend = "plotly"

janbenetka

CREATE TABLE dataset.new_table
PARTITION BY DATE(timestamp_column) AS
SELECT x, y, z, timestamp_column
FROM dataset.existing_table

CREATE OR REPLACE TABLE `uc-prox-core-dev.14_days_retention.home_od_flux_2020_aggregated_condensed` 
PARTITION BY minProcessingDate
AS
SELECT...

janbenetka

import pandas as pd 
pd.options.display.max_columns = 50  # None -> No Restrictions
pd.options.display.max_rows = 200    # None -> Be careful with this 
pd.options.display.max_colwidth = 100
pd.options.display.precision = 3

janbenetka

df = pd.DataFrame(dict(A=[2,6,3],
                       B=[2,2,6], 
                       C=[3,2,3]))
df['col_total']     = df.apply(lambda x: x.sum(), axis=1)
df.loc['row_total'] = df.apply(lambda x: x.sum())