from __future__ import print_function
%matplotlib inline

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_context("talk")

with np.load("data_files.npz") as data:
    X_train = data['X_train']
    Y_train = data['Y_train']
    X_test = data['X_test']
    Y_test = data['Y_test']
    X_comp = data['X_comp']
del data

X_train = np.float64(X_train)
X_test = np.float64(X_test)
X_comp = np.float64(X_comp)

X_train.shape

plt.plot(X_train[0])

def convert_to_spectra(X):
    out = []
    for row in X:
        # Compute frequency sprectrum
        xfft = np.fft.fft(row)
        n = len(xfft)
        
        # Fold negative frequencies and drop DC component
        half_n = np.ceil(n/2.0)
        xfft = (2.0 / n) * xfft[1:half_n]
        
        out.append(np.abs(xfft))
    out = np.array(out)
    return out

X_train_spectra = convert_to_spectra(X_train)
X_test_spectra = convert_to_spectra(X_test)
X_comp_spectra = convert_to_spectra(X_comp)

X_train_spectra.shape

plt.plot(X_train_spectra[0])
plt.xlabel("Frequency")
plt.ylabel("Amplitude")

def moving_average(X, n=3):
    ret = []
    for row in X:
        row = np.cumsum(row)
        row[n:] = row[n:] - row[:-n]
        row = row[n - 1:] / n
        ret.append(row)
    ret = np.array(ret)
    return ret

X_train_spectra_no_average = X_train_spectra
X_train_spectra = moving_average(X_train_spectra, n=5)
X_test_spectra = moving_average(X_test_spectra, n=5)
X_comp_spectra = moving_average(X_comp_spectra, n=5)

plt.subplot(2, 1, 1)
plt.plot(X_train_spectra_no_average[0])
plt.ylabel("Unaveraged Amplitude")
plt.subplot(2, 1, 2)
plt.plot(X_train_spectra[0])
plt.ylabel("Averaged Amplitude")
plt.xlabel("Frequency")

print(X_train_spectra.min(), X_train_spectra.max())
print(X_test_spectra.min(), X_test_spectra.max())
print(X_comp_spectra.min(), X_comp_spectra.max())

X_train_spectra = np.int16(X_train_spectra)
X_test_spectra = np.int16(X_test_spectra)
X_comp_spectra = np.int16(X_comp_spectra)

for_google = np.c_[Y_train, X_train_spectra]
# np.savetxt("X_train_spectra_ave_goog.csv", for_google, delimiter=",", fmt='%i')

print(X_train_spectra.shape)
print(Y_train.shape)
print(X_test_spectra.shape)
print(Y_test.shape)
print(X_comp_spectra.shape)

from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators=100, verbose=True,max_depth=None,min_samples_split=1, random_state=0)
model.fit(X_train_spectra,Y_train)

my_score = model.score(X_test_spectra,Y_test)
print(my_score)

from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

Y_pred = model.predict(X_test_spectra)

accuracy_score(Y_test, Y_pred)

for_google.shape

print(classification_report(Y_test, Y_pred))

confusion_matrix(Y_test, Y_pred, labels=[0, 1])

plt.plot(model.feature_importances_)
plt.ylabel("Relative Feature Importance")
plt.xlabel("Frequency")