#!/usr/bin/env python
# coding: utf-8

# # Quickstart

# We download some test data for the 32 tables from the address below and populate the Concept registry.

# In[ ]:


get_ipython().system('wget -nc https://physionet.org/static/published-projects/mimic-iv-demo-omop/mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip')
get_ipython().system('unzip -n mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip')


# Create a test instance:

# In[ ]:


get_ipython().system('lamin init --storage ./test-omop --name test-omop --schema omop')


# Import `omop`:

# In[ ]:


import lamindb as ln
import omop as op
import pandas as pd


# Load the data into a Pandas DataFrame:

# In[ ]:


df = pd.read_csv("./mimic-iv-demo-data-in-the-omop-common-data-model-0.9/1_omop_data_csv/2b_concept.csv")
df.columns = df.columns.str.lower()
df.rename(columns={"concept_class_id": "concept_class"}, inplace=True)
df.head()


# Populate the Concept registry:

# In[ ]:


concepts = [op.Concept(**row.to_dict()) for _, row in df.iterrows()]
for concept in concepts:
    concept.save()
op.Concept.df()


# Perform validation of new data.

# In[ ]:


op.Concept.validate(["Stroke Volume Variation", "this concept does not exist"], field=op.Concept.concept_name)