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

# # Running Inference on Legacy (Non-SageWorks) Models
# This notebook goes through the steps of setting up and running inference on Models that weren't generated in SageWorks.
# 
# ```
# model = Model("the old model")
# model.onboard()
# ```
# Answer all the Model onboarding questions, the tricky one is 'features' (note: capitalization matters)
# 
# ```
# end = Endpoint("the old endpoint")
# end.onboard()
# ```
# 
# Answer all the onboard questions, if you're asked for input put the Model Name.
# 
# After this is done, you'll need follow this notebook for 'remapping' the evaluation data into a form that the old model can use.

# In[ ]:


import os

# Set the environment variable
os.environ['SAGEWORKS_CONFIG'] = '/Users/briford/.sageworks/scp_sandbox.json'


# In[ ]:


# Grab the features from the model (this will be set during onboard())
from sageworks.api.model import Model
model = Model("LogS-pH7-Class-0-231025")
target = model.target()
print(target)
features = model.features()
print(f"{features[:5]}...")


# In[ ]:


# Grab the evaluation data
from sageworks.api.feature_set import FeatureSet
fs = FeatureSet("solubility_featurized_fs")
training_view = fs.view("training").table
eval_data = fs.query(f"select * from {training_view} where training=0")


# In[ ]:


data_columns = eval_data.columns


# In[ ]:


def build_map(data_columns, features):
    map = dict()
    for f in features:
        if f.lower() in data_columns:
            map[f.lower()] = f
    return map


# In[ ]:


map = build_map(data_columns, features)
map["class"] = target  # Add the target variable name change


# In[ ]:


# Rename the feature and target columns to 'match' what the Legacy Model expects
eval_data.rename(columns=map, inplace=True)


# In[ ]:


# Grab the Legacy Endpoint
from sageworks.api.endpoint import Endpoint
end = Endpoint("LogS-pH7-Class-0-231025")


# In[ ]:


# Run inference on the Legacy Endpoint
end.inference(eval_data, capture_uuid="2024_03_19_holdout")


# In[ ]:


# This might not be strictly necssary but it will make sure the details are up to date
model.details(recompute=True)