def _new_dataset_for_updating(client):
# new dataset
airline_csv = str(
Path(__file__).parents[1]) + "/data/AirlineComplaints.csv"
dataset = client.call(
CreateDataset(name=f"AddDataToWorkflow-test-{int(time.time())}",
files=[airline_csv]))
# new teach task
questionnaire = client.call(
CreateQuestionaire(
name=f"AddDataToWorkflowTeach-test-{int(time.time())}",
dataset_id=dataset.id,
targets=["positive", "negative"],
))
assert questionnaire.num_total_examples > 0
# add data to dataset and process
dataset = client.call(AddFiles(dataset_id=dataset.id, files=[airline_csv]))
datafile_ids = [f.id for f in dataset.files]
dataset = client.call(
ProcessCSV(dataset_id=dataset.id, datafile_ids=datafile_ids,
wait=True))
assert dataset.status == "COMPLETE"
# get workflow
wfs = client.call(ListWorkflows(dataset_ids=[dataset.id]))
wf = max(wfs, key=lambda w: w.id)
return dataset, wf, questionnaire
def too_small_dataset(indico):
client = IndicoClient()
dataset_filepath = str(Path(__file__).parents[0]) + "/TooSmall.csv"
response = client.call(
CreateDataset(name=f"TooSmall-test-{int(time.time())}",
files=[dataset_filepath]))
assert response.status == "COMPLETE"
return response
def org_annotate_dataset(indico):
client = IndicoClient()
dataset_filepath = str(
Path(__file__).parents[0]) + "/org-annotate-labeled.csv"
response = client.call(
CreateDataset(name=f"OrgAnnotate-test-{int(time.time())}",
files=[dataset_filepath]))
assert response.status == "COMPLETE"
return response
def airlines_dataset(indico):
client = IndicoClient()
dataset_filepath = str(
Path(__file__).parents[0]) + "/AirlineComplaints.csv"
response = client.call(
CreateDataset(name=f"AirlineComplaints-test-{int(time.time())}",
files=[dataset_filepath]))
assert response.status == "COMPLETE"
return response
def cats_dogs_image_dataset(indico):
client = IndicoClient()
dataset_filepath = str(
Path(__file__).parents[0]) + "/dog_vs_cats_small.csv"
response = client.call(
CreateDataset(
name=f"DogsAndCats-test-{int(time.time())}",
files=dataset_filepath,
from_local_images=True,
))
assert response.status == "COMPLETE"
return response
below shows you what to do if the images are on your computer.
"""
from indico import IndicoClient, IndicoConfig
from indico.queries import CreateDataset
import pandas as pd
# Create an Indico API client
my_config = IndicoConfig(host="app.indico.io",
api_token_path="./path/to/indico_api_token.txt")
client = IndicoClient(config=my_config)
# With local images you should create a CSV formatted (here for demonstration) like below
# Where one column contains the paths from the csv to where the images are stored on your computer
image_dataset = pd.DataFrame()
image_dataset["image_files"] = [
"./path/from/csv/to/image.png",
"./path/from/csv/to/image2.png",
]
image_dataset.to_csv("./image_dataset.csv", index=False)
# Use the CSV you created (like above) to create the dataset
dataset = client.call(
CreateDataset(
name="My Image Dataset",
files="./image_dataset.csv",
from_local_images=True,
image_filename_col=
"image_files", # specify the column containing the images
))
from indico import IndicoClient, IndicoConfig
from indico.queries import CreateDataset, CreateModelGroup, ModelGroupPredict
# Create an Indico API client
my_config = IndicoConfig(host="app.indico.io",
api_token_path="./path/to/indico_api_token.txt")
client = IndicoClient(config=my_config)
# create the dataset
dataset = client.call(
CreateDataset(name="airline_comments", files=["./airline-comments.csv"]))
# train the model w/ the relevant csv columns
model_group = client.call(
CreateModelGroup(
name="my_classification_model",
dataset_id=dataset.id,
source_column_id=dataset.datacolumn_by_name(
"text").id, # csv text column
labelset_id=dataset.labelset_by_name(
"Target_1").id, # csv target class column
wait=True, # wait for training to finish
))
# predict on the model
job = client.call(
ModelGroupPredict(
model_id=model_group.selected_model.id,
data=["Sample Text to predict on", "More Sample text to predict on"],
))