import numpy as np
import gradio as gr

import pandas as pd


def homework01_solution2(question, K, X1, X2):

  K = int(K)

  # Verify your solutions by code
  import numpy as np
  import pandas as pd
  X = np.array([[-1,1],
              [0,1],
              [0,2],
              [1,-1],
              [1,0],
              [1,2],
              [2,2],
              [2,3]])
  if question == 'Question 2':
      y = np.array([1,0,1,1,0,0,1,0])
  else:
      y = np.array([0,1,0,0,1,1,0,1])

        
  train_data = pd.DataFrame(X, columns=['X1', 'X2'])
  train_data['Label (Y)'] = y

  from sklearn.neighbors import KNeighborsClassifier
  #(1) predict class for point (3,3) with K = 3

  neigh = KNeighborsClassifier(n_neighbors=K)
  neigh.fit(X, y)

  pred = neigh.predict(X)
  train_data['Predicted Label ('+str(K)+'-NN)'] = pred
    
  predicted_label = neigh.predict(np.array([[X1, X2]]))[0]

  (nb_dist, nb_indice) = neigh.kneighbors(np.array([[X1, X2]]), K)

  import pandas as pd

  results = pd.DataFrame(columns=['Rank of closest neighbor', 'Features (X_1,X_2)', 	'Label (Y)', 	'Distance to query data'])

  for i in range(K):
    idx = nb_indice[0][i]
    fea = X[idx].tolist()
    fea = '({})'.format(', '.join(map(str, fea)))

    dist = nb_dist[0][i]
    label = y[idx]

    #print(idx, fea, dist, label)

    # Dictionary to append
    new_data = {'Rank of closest neighbor': i, 'Features (X_1,X_2)': fea, 	'Label (Y)':label , 	'Distance to query data': dist}
    tmp = pd.DataFrame(new_data, index=[0])
    # Append dictionary to DataFrame
    #data = data.append(new_data, ignore_index=True)
    results = pd.concat([results, tmp], ignore_index=True)

  results = results.sort_values(by='Rank of closest neighbor')
  results['Distance to query data'] = results['Distance to query data'].round(3)
  results


  #Task 2:  Based on predicted labels and actual labels provided in the above table, what's the number of correct predictions?
  # Initialize a counter for correct predictions
  correct_predictions = 0
  for actual, predicted in zip(y, pred):
    if actual == predicted:
        correct_predictions += 1
  
  #Task 3: What's the total number of predictions?
  total_predictions = len(y)
 

  #Task 4: What's the classification accuracy?
  acc = np.round(correct_predictions/total_predictions,3)

 

  #Task 5: What's the classification error?
  err = 1 - acc
  
  return train_data, results, predicted_label, correct_predictions, total_predictions, acc, err




### configure inputs
set_question = gr.Number(value=7)


set_question = gr.Dropdown(
            ["Question 2",
             "Question 4"], 
              value="Question 2", label="Select question"
        )


set_K = gr.Number(value=7)
set_X1 = gr.Number(value=1)
set_X2 = gr.Number(value=2)

### configure outputs
set_output_traindata = gr.Dataframe(type='pandas', label ='Train Dataset')
set_output_q1a = gr.Dataframe(type='pandas', label ='Question 2: KNN-Classifier Search')
set_output_q1b = gr.Textbox(label ='Question 2: KNN-Classifier Prediction')
set_output_q4b = gr.Textbox(label ='Question 4b: Number of correct prediction')
set_output_q4c = gr.Textbox(label ='Question 4c: Total number of prediction')
set_output_q4d = gr.Textbox(label ='Question 4d: Classfication Accuracy')
set_output_q4e = gr.Textbox(label ='Question 4e: Classfication Error')

### configure Gradio
interface = gr.Interface(fn=homework01_solution2, 
                         inputs=[set_question, set_K, set_X1, set_X2], 
                         outputs=[set_output_traindata, set_output_q1a, set_output_q1b, set_output_q4b, set_output_q4c, set_output_q4d, set_output_q4e],
                         
                         title="CSCI4750/5750(hw01-PartI): Mathematics for KNN (Question 2 & 4: KNN-Classifier Search)", 
                         description= "Click examples below for a quick demo",
                         theme = 'huggingface'
                         )


interface.launch(debug=True)