ium_434784/training.py

import sys
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os
from countries_map import countries
import tensorflow as tf
from tensorflow.keras.layers import Input, Dense, Activation, Dropout
from tensorflow.keras.models import Model
from tensorflow.keras.callbacks import EarlyStopping
from keras.models import Sequential
from sklearn.metrics import mean_squared_error
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.layers.experimental import preprocessing

EPOCHS = int(sys.argv[1])
BATCH_SIZE = int(sys.argv[2])

age = {"5-14 years": 0, "15-24 years": 1, "25-34 years": 2,
       "35-54 years": 3, "55-74 years": 4, "75+ years": 5}
sex = {"male": 0, "female": 1}

# wczytanie danych
sc = pd.read_csv('who_suicide_statistics.csv')
print(sc.shape)

# Usunięcie niepełnych danych
sc.dropna(inplace=True)

# Kategoryzacja
sc = pd.get_dummies(
    sc, columns=['age', 'sex', 'country'], prefix='', prefix_sep='')


# podział na train validate i test
train, validate, test = np.split(sc.sample(frac=1, random_state=42),
                                 [int(.6*len(sc)), int(.8*len(sc))])

# podział train set
X_train = train.loc[:, train.columns != 'suicides_no']
y_train = train[['suicides_no']]
X_test = test.loc[:, train.columns != 'suicides_no']
y_test = test[['suicides_no']]

normalizer = preprocessing.Normalization()
normalizer.adapt(np.array(X_train))

first = np.array(X_train[:1])
with np.printoptions(precision=2, suppress=True):
    print('First example:', first)
    print()
    print('Normalized:', normalizer(first).numpy())

model = tf.keras.Sequential([
    normalizer,
    layers.Dense(units=1)
])
model.predict(X_train[:10])

# Compile model
model.compile(
    optimizer=tf.optimizers.Adam(learning_rate=0.1),
    loss='mean_absolute_error')

# Train model
history = model.fit(
    X_train, y_train,
    batch_size=BATCH_SIZE,
    epochs=EPOCHS,
    validation_split=0.2)

model.save_weights('suicide_model.h5')

test_results = {}

test_results['model'] = model.evaluate(
    X_test, y_test, verbose=0)

test_predictions = model.predict(X_test).flatten()

# a = plt.axes(aspect='equal')
# plt.scatter(y_test, test_predictions)
# plt.xlabel('True values [sucides_no]')
# plt.ylabel('Predictions values [sucides_no]')
# lims = [0, 5000]
# plt.xlim(lims)
# plt.ylim(lims)
# _ = plt.plot(lims, lims)

# plt.show()

predictions = model.predict(X_test)
pd.DataFrame(predictions).to_csv('results.csv')
model.summary()