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

# # Semantic Segmentation Input

# ## Install Dependencies

# In[1]:


get_ipython().system('pip install -r requirements.txt')


# ## Setup Imports

# In[2]:


from auxiliary.nifti.io import read_nifti
from rich import print as pprint
from panoptica import (
    InputType,
    Panoptica_Evaluator,
    ConnectedComponentsInstanceApproximator,
    NaiveThresholdMatching,
)


# ## Load Data

# To demonstrate we use a reference and predicition of spine a segmentation without instances.
# 
# ![semantic_figure](figures/semantic.png)

# In[3]:


ref_masks = read_nifti("./spine_seg/semantic/ref.nii.gz")
pred_masks = read_nifti("./spine_seg/semantic/pred.nii.gz")


# To use your own data please replace the example data with your own data.
# 
# In ordner to successfully load your data please use NIFTI files  and the following file designation within the "semantic" folder: 
# 
# ```panoptica/spine_seg/semantic/```
# 
# - Reference data ("ref.nii.gz")
# - Prediction data ("pred.nii.gz")
# 

# ## Run Evaluation

# In[4]:


evaluator = Panoptica_Evaluator(
    expected_input=InputType.SEMANTIC,
    instance_approximator=ConnectedComponentsInstanceApproximator(),
    instance_matcher=NaiveThresholdMatching(),
)


# ## Inspect Results
# The results object allows access to individual metrics and provides helper methods for further processing
# 

# In[5]:


# print all results
result, intermediate_steps_data = evaluator.evaluate(
    pred_masks, ref_masks, verbose=False
)["ungrouped"]
print(result)


# In[6]:


# get specific metric, e.g. pq
pprint(f"{result.pq=}")


# In[7]:


# get dict for further processing, e.g. for pandas
pprint("results dict: ", result.to_dict())


# In[8]:


# To inspect different phases, just use the returned intermediate_steps_data object

import numpy as np

intermediate_steps_data.original_prediction_arr  # yields input prediction array
intermediate_steps_data.original_reference_arr  # yields input reference array

intermediate_steps_data.prediction_arr(
    InputType.MATCHED_INSTANCE
)  # yields prediction array after instances have been matched
intermediate_steps_data.reference_arr(
    InputType.MATCHED_INSTANCE
)  # yields reference array after instances have been matched

# This works with all InputType
for i in InputType:
    print(i)
    pred = intermediate_steps_data.prediction_arr(i)
    ref = intermediate_steps_data.reference_arr(i)
    print("Prediction array shape =", pred.shape, "unique_values=", np.unique(pred))
    print("Reference array shape =", ref.shape, "unique_values=", np.unique(ref))
    print()