import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
import seaborn as sns
from sklearn.preprocessing import LabelEncoder
import pickle
import streamlit as st 

st.title('Repair Time Prediction')
#DLoading the ataset
#df = pd.read_csv('repair_time_sample_50k_modified2.csv')

#new_data = df
#df.drop(['SRU serial number','Date of Manufacture', 'Snag Description'], axis = 1, inplace=True)


# DATA from user
def user_report():
  Aircraft_Type = st.sidebar.selectbox('Aircraft Type',("AH-64","UH-60","UH-63","UH-62","UH-61","AH-65"))
  if Aircraft_Type=="AH-64":
      Aircraft_Type=0
  elif Aircraft_Type=="UH-60":
      Aircraft_Type=2
  elif Aircraft_Type=="UH-63":
      Aircraft_Type=5
  elif Aircraft_Type=="UH-62":
      Aircraft_Type=4
  elif Aircraft_Type=="UH-61":
      Aircraft_Type=3
  else:
      Aircraft_Type=1
  manufacturer = st.sidebar.selectbox("Manufacturer",
        ("JKL Company", "GHI Company","AGS Company","ABC Company","XYZ Company" ))
  if manufacturer=='JKL Company':
      manufacturer=3
  elif manufacturer=="GHI Company":
      manufacturer=2
  elif manufacturer=="AGS Company":
      manufacturer=1
  elif manufacturer=="ABC Company":
      manufacturer =0
  else:
      manufacturer=4
  component_age = st.sidebar.slider('Component Age (in hours)', 500,2000, 600 )
  Issue_category= st.sidebar.selectbox("Issue Category",
        ("Display", "Unservicable","Bootup Problem","Engine Failure","Electrical Fault" ))
  if Issue_category=='Display':
      Issue_category=1
  elif Issue_category=="Unservicable":
      Issue_category=4
  elif Issue_category=="Bootup Problem":
      Issue_category=0
  elif Issue_category=="Engine Failure":
      Issue_category=3
  else:
      Issue_category=2
  Snag_Severity	= st.sidebar.selectbox("Snag Severity",
        ("Low", "Medium","High" ))
  if Snag_Severity	=='Low':
      Snag_Severity=1
  elif Snag_Severity=="Medium":
      Snag_Severity	=2
  else:
       Snag_Severity=0
  Customer= st.sidebar.selectbox("Customer",
        ("IAF", "ARMY","NAVY" ))
  if Customer	=='IAF':
      Customer=1
  elif Customer=="ARMY":
      Customer	=0
  else:
       Customer=2
  Technician_Skill_level= st.sidebar.selectbox("Technician Skill level",
        ("Expert", "Intermediate","Novice" ))
  if Technician_Skill_level	=='Expert':
      Technician_Skill_level=0
  elif Technician_Skill_level=="Intermediate":
      Technician_Skill_level	=1
  else:
       Technician_Skill_level=2
  prior_maintainence = st.sidebar.selectbox('Prior Maintainence',("Regular","Irregular"))
  if prior_maintainence =='Regular':
      prior_maintainence=1
  else:
      prior_maintainence=0
  Logistics_Time = st.sidebar.slider('Logistics Time (hr)', 2,21, 5 )
  total_operating_hours = st.sidebar.slider('Total Operating Hours)', 50,2000, 500 )
  operating_temperature = st.sidebar.slider('Operating Temperature', 10,25, 15 )
  previous_number_of_repairs = st.sidebar.number_input('Enter the Previous Number of Repairs Undergone  0 to 3 )',min_value=0,max_value=3,step=1)
  Power_Input_Voltage= st.sidebar.slider('Power Input Voltage (V)',100,133,115)  


  user_report_data = {
      'Aircraft Type':Aircraft_Type,
      'Manufacturer':manufacturer,
      'Component_Age':component_age,
      'Issue_category':Issue_category,
      'Snag Severity': Snag_Severity,
      'Customer':Customer,
      'Technician Skill level':Technician_Skill_level,
      'Prior Maintenance': prior_maintainence,
      'Logistics Time (hr)':Logistics_Time,
      'total_operating_hours':total_operating_hours,
      'operating_temperature':operating_temperature,
      'previous_number_of_repairs':previous_number_of_repairs,
      'Power_Input_Voltage':Power_Input_Voltage
           
  }
  report_data = pd.DataFrame(user_report_data, index=[0])
  return report_data    
    
#Customer Data
user_data = user_report()
st.header("Component Details")
st.write(user_data)

def preprocess_dataset(X):  
  x = X.values #returns a numpy array
  min_max_scaler = preprocessing.MinMaxScaler()
  x_scaled = min_max_scaler.fit_transform(x)
  X_df = pd.DataFrame(x_scaled)
  return X_df

def label_encoding(data):
  le = LabelEncoder()
  cat = data.select_dtypes(include='O').keys()
  categ = list(cat)
  data[categ] = data[categ].apply(le.fit_transform)
  # X = data.loc[:,data.columns!= "Time required for repair (in hours)"]
  # y = data['Time required for repair (in hours)']
  # return X,y
  return data

def prediction(df):
  #X = df.loc[:,df.columns!= "Time required for repair (in hours)"]
  #y = df['Time required for repair (in hours)']
  #X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=42)
  #print(X_train.shape)
  #print(X_test.shape)
  #X_test_encoded = label_encoding(df)
  #X_test_df = preprocess_dataset(df)
  x_model = pickle.load(open('repair_time_model.pkl','rb'))
  pred = x_model.predict(df)
  #X_test['Actual_time_to_repair'] = y_test
  #X_test['Predicted_time_to_repair'] = pred
  #X_test.to_csv(r'/content/drive/MyDrive/Colab Notebooks/HAL/repair_time_prediction_results.csv')
  #print(X_test.head())
  return pred
    
y_pred = prediction(user_data)

if st.button("Predict"):
    st.subheader(f"Time required to Repair the Component is {y_pred[0]} hours")