from keras.models import Sequential
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn import metrics
import math
import numpy as np


def write_list(names):
    with open('listfile.txt', 'w') as fp:
        fp.write("\n".join(str(item) for item in names))

def get_x_y(data):
    lb = LabelEncoder()

    data = data.drop(["Location 1"], axis=1)
    data = data.drop(columns=["Longitude", "Latitude", "Location", "Total Incidents", "CrimeTime", "Neighborhood", "Post", "CrimeDate", "Inside/Outside"], axis=1)
    for column_name in data.columns:
        data[column_name] = lb.fit_transform(data[column_name])
    x = data.drop('Weapon', axis=1)
    y = data['Weapon']



    return data, x, y


def predict():
    model = load_model('baltimore_model.h5')

    train = pd.read_csv('baltimore_train.csv')
    baltimore_data_test = pd.read_csv('baltimore_test.csv')
    baltimore_data_test.columns = train.columns
    baltimore_data_test, x_test, y_test = get_x_y(baltimore_data_test)
    scores = model.evaluate(x_test, y_test)
    print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1] * 100))

    y_predicted = model.predict(x_test)
    y_predicted = np.argmax(y_predicted,axis=1)
    test_results = {}
    test_results['Weapon'] = model.evaluate(
        x_test,
        y_test, verbose=0)
    write_list(y_predicted)

predict()