Connect Soda to Dask and Pandas

import dask.datasets
import pandas as pd
from soda.scan import Scan

# Create a Soda scan object
scan = Scan()

# Load timeseries data from dask datasets
df_timeseries = dask.datasets.timeseries().reset_index()
df_timeseries["email"] = "a@soda.io"

# Create an artificial pandas dataframe
df_employee = pd.DataFrame({"email": ["a@soda.io", "b@soda.io", "c@soda.io"]})

# Either add Dask dataframe to scan and assign a dataset name to refer from checks.yaml
scan.add_dask_dataframe(dataset_name="timeseries", dask_df=df_timeseries, data_source_name="orders")
# OR, add Pandas dataframe to scan and assign a dataset name to refer from checks.yaml
scan.add_pandas_dataframe(dataset_name="employee", pandas_df=df_employee, data_source_name="orders")

# Optionally, add multiple dataframes as unique data sources. Note the change of 
# the data_source_name parameter. 
scan.add_dask_dataframe(dataset_name="inquiries", dask_df=[...], data_source_name="customers")

# Set the scan definition name and default data source to use
scan.set_scan_definition_name("test")
scan.set_data_source_name("orders")

# Add configuration YAML file
# You do not need connection to a data source; you must have a connection to Soda Cloud
# Choose one of the following two options:
# 1) From a file
scan.add_configuration_yaml_file(file_path="~/.soda/configuration.yml")
# 2) Inline in the code
# For host, use cloud.soda.io for EU region; use cloud.us.soda.io for US region
scan.add_configuration_yaml_str(
    """
    soda_cloud:
      host: cloud.soda.io
      api_key_id: 2e0ba0cb-your-api-key-7b
      api_key_secret: 5wd-your-api-key-secret-aGuRg
"""

# Define checks in yaml format
# Alternatively, refer to a yaml file using scan.add_sodacl_yaml_file(<filepath>)
checks = """
for each dataset T:
  datasets:
    - include %
  checks:
    - row_count > 0
profile columns:
  columns:
    - employee.%
checks for employee:
    - values in (email) must exist in timeseries (email) # Error expected
    - row_count same as timeseries # Error expected
checks for timeseries:
  - avg_x_minus_y between -1 and 1:
      avg_x_minus_y expression: AVG(x - y)
  - failed rows:
      samples limit: 50
      fail condition: x >= 3
  - schema:
      name: Confirm that required columns are present
      warn:
        when required column missing: [x]
        when forbidden column present: [email]
        when wrong column type:
          email: varchar
      fail:
        when required column missing:
          - y
  - invalid_count(email) = 0:
      valid format: email
  - valid_count(email) > 0:
      valid format: email
"""

scan.add_sodacl_yaml_str(checks)

scan.set_verbose(True)
scan.execute()

import pandas as pd
from soda.scan import Scan

# Create a Soda scan object
scan = Scan()

# Load JSON file into DataFrame
df = pd.read_json('your_file.json')

...