gsion1
commented
3 years ago I did that, but the confusion matrix shows that there is an error somewhere, maybe in the confusion matrix itself and not the prediction
After the initila code, the confusion matrix is the one bellow (not a lot of errors)
Many lines should be removed but here is the code
#https://kgptalkie.com/human-activity-recognition-using-accelerometer-data/
import tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Flatten, Dense, Dropout, BatchNormalization
from tensorflow.keras.layers import Conv2D, MaxPool2D
from tensorflow.keras.optimizers import Adam
#print(tf.__version__)
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
file = open('WISDM_ar_v1.1_raw.txt')
#file = open('jogging.txt')
lines = file.readlines()
processedList = []
for i, line in enumerate(lines):
try:
line = line.split(',')
last = line[5].split(';')[0]
last = last.strip()
if last == '':
break;
temp = [line[0], line[1], line[2], line[3], line[4], last]
processedList.append(temp)
except:
print('Error at line number: ', i)
columns = ['user', 'activity', 'time', 'x', 'y', 'z']
data = pd.DataFrame(data = processedList, columns = columns)
data.head()
data.shape
data.info()
data.isnull().sum()
data['activity'].value_counts()
data['x'] = data['x'].astype('float')
data['y'] = data['y'].astype('float')
data['z'] = data['z'].astype('float')
data.info()
Fs = 20 #sampling rate in Hz
activities = data['activity'].value_counts().index
df = data.drop(['user', 'time'], axis = 1).copy()
df.head()
df['activity'].value_counts()
label = LabelEncoder()
df['label'] = label.fit_transform(df['activity'])
df.head()
X = df[['x', 'y', 'z']]
y = df['label']
scaler = StandardScaler()
X = scaler.fit_transform(X)
scaled_X = pd.DataFrame(data = X, columns = ['x', 'y', 'z'])
scaled_X['label'] = y.values
scaled_X.head()
import scipy.stats as stats
#divide the samplings in 4s frames
Fs = 20 #sampling is 20Hz
frame_size = Fs*4 # 80samples, 4 secondes
hop_size = Fs*2 # 40
def get_frames(df, frame_size, hop_size):
N_FEATURES = 3
frames = []
labels = []
for i in range(0, len(df) - frame_size, hop_size):
x = df['x'].values[i: i + frame_size]
y = df['y'].values[i: i + frame_size]
z = df['z'].values[i: i + frame_size]
# Retrieve the most often used label in this segment
label = stats.mode(df['label'][i: i + frame_size])[0][0]
frames.append([x, y, z])
labels.append(label)
# Bring the segments into a better shape
frames = np.asarray(frames).reshape(-1, frame_size, N_FEATURES)
labels = np.asarray(labels)
return frames, labels
X, y = get_frames(scaled_X, frame_size, hop_size)
#still match with the right labels
X.shape, y.shape
X = X.reshape(X.shape[0],80,3,1)
X.shape
import keras
model = keras.models.load_model('model.h5')
from mlxtend.plotting import plot_confusion_matrix
from sklearn.metrics import confusion_matrix
print(model.predict(X))
y_pred = np.argmax(model.predict(X), axis=-1)
print(y_pred)
label_list = ["Walking", "Jogging", "Upstairs", "Downstairs", "Sitting", "Standing"]
draw_mat = 1
if draw_mat:
mat = confusion_matrix(y, y_pred)
plot_confusion_matrix(conf_mat=mat, class_names=label_list, show_normed=True, figsize=(7,7))`
laxmimerit
guillaume55
superuser28
Hi, Thanks for this tutorial. Could you add an example describing how to predict a small batch of 80 x,y,z data with the saved model please? Thanks a lot Guillaume