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

# Now that we have build our model, let's make future predictions. As a reminder, our plan of action was as follows:
# 
# 1. Perform EDA on the dataset to extract valuable insight about the process generating the time series **(COMPLETED)**.
# 2. Build a baseline model (univariable model without exogenous variables) for benchmarking purposes **(COMPLETED)**.
# 3. Build a univariate model with all exogenous variables to check best possible performance **(COMPLETED)**.
# 4. Evaluate the model with exogenous variables and discuss any potential issues **(COMPLETED)**.
# 5. Overcome issues identified above **(COMPLETED)**.
# 6. Make future predictions with the best model. **(Covered in this notebook)**
# 7. Replicate flow with Automated Time Series Modeling (AutoML)

# In[1]:


# Only enable critical logging (Optional)
import os
os.environ["PYCARET_CUSTOM_LOGGING_LEVEL"] = "CRITICAL"


# In[2]:


def what_is_installed():
    from pycaret import show_versions
    show_versions()

try:
    what_is_installed()
except ModuleNotFoundError:
    get_ipython().system('pip install pycaret')
    what_is_installed()


# In[3]:


import numpy as np
import pandas as pd
from pycaret.datasets import get_data
from pycaret.time_series import TSForecastingExperiment


# In[4]:


# Global Figure Settings for notebook ----
global_fig_settings = {"renderer": "notebook", "width": 1000, "height": 600}


# In[5]:


data = get_data("airquality", verbose=False)
data["index"] = pd.to_datetime(data["Date"] + " " + data["Time"])
data.drop(columns=["Date", "Time"], inplace=True)
data.replace(-200, np.nan, inplace=True)
data.set_index("index", inplace=True)

exog_vars = ['NOx(GT)', 'PT08.S3(NOx)', 'RH']
data = data[exog_vars]
data.head()


# # Step 6: Making Future Predictions
# 
# # Step 6A: Get future exogenous variable values using forecasting

# In[6]:


exog_exps = []
exog_models = []
for exog_var in exog_vars:
    exog_exp = TSForecastingExperiment()
    exog_exp.setup(
        data=data[exog_var], fh=48,
        numeric_imputation_target="ffill", numeric_imputation_exogenous="ffill",
        fig_kwargs=global_fig_settings, session_id=42
    )

    # Users can customize how to model future exogenous variables i.e. add
    # more steps and models to potentially get better models at the expense
    # of higher modeling time.
    best = exog_exp.compare_models(
        sort="mase", include=["arima", "ets", "exp_smooth", "theta", "lightgbm_cds_dt",]        
    )
    final_exog_model = exog_exp.finalize_model(best)

    exog_exps.append(exog_exp)
    exog_models.append(final_exog_model)

# Step 2: Get future predictions for exog variables ----
future_exog = [
    exog_exp.predict_model(exog_model)
    for exog_exp, exog_model in zip(exog_exps, exog_models)
]
future_exog = pd.concat(future_exog, axis=1)
future_exog.columns = exog_vars


# In[7]:


future_exog


# # Step 6B: Load Model and make future predcitons for the target variable

# In[8]:


exp_future = TSForecastingExperiment()


# In[9]:


final_slim_model = exp_future.load_model("final_slim_model")


# In[10]:


future_preds = exp_future.predict_model(final_slim_model, X=future_exog)
future_preds.plot()