I have trained a deep learning model, save it with and now I want to hit a web service in order to get pack a category. This is the first time I try to do that so I am a little confused. I can not figure out how to take categories back. Also when I write http://localhost:8000/predict I get back Method Not Allowed
The method is not allowed for the requested URL. The code so far is below
from flask import Flask,request, jsonify#--jsonify will return the data
import os
from keras.models import load_model
app = Flask(__name__)
os.chdir(r'C:\Users\aggelos\Desktop\flask')
model = load_model(os.path.join(os.getcwd(), "lstm-final-five-Copy1.h5"))
@app.route('/')
def getmodel():
return str (model)
@app.route('/predict', methods= ["POST"])
def predict():
a1= pd.read_csv("sitting 1.csv")
a1.insert(0, 'activity', "sitting")
b1= pd.read_csv("standing 1.csv")
b1.insert(0, 'activity', "standing")
c1= pd.read_csv("walking 1.csv")
c1.insert(0, 'activity', "walking")
d1= pd.read_csv("jogging 1.csv")
d1.insert(0, 'activity', "jogging")
e1= pd.read_csv("upstairs 1.csv")
e1.insert(0, 'activity', "upstairs")
f1= pd.read_csv("downstairs 1.csv")
f1.insert(0, 'activity', "downstairs")
df1 = pd.concat([a1, b1, c1 , d1, e1 ,f1])
a2= pd.read_csv("sitting 2.csv")
a2.insert(0, 'activity', "sitting")
b2= pd.read_csv("standing 2.csv")
b2.insert(0, 'activity', "standing")
c2= pd.read_csv("walking 2.csv")
c2.insert(0, 'activity', "walking")
d2= pd.read_csv("jogging 2.csv")
d2.insert(0, 'activity', "jogging")
e2= pd.read_csv("upstairs 2.csv")
e2.insert(0, 'activity', "upstairs")
f2= pd.read_csv("downstairs 2.csv")
f2.insert(0, 'activity', "downstairs")
df2 = pd.concat([a2, b2, c2 , d2, e2 ,f2])
a3= pd.read_csv("sitting 3.csv")
a3.insert(0, 'activity', "sitting")
b3= pd.read_csv("standing 3.csv")
b3.insert(0, 'activity', "standing")
c3= pd.read_csv("walking 3.csv")
c3.insert(0, 'activity', "walking")
d3= pd.read_csv("jogging 3.csv")
d3.insert(0, 'activity', "jogging")
e3= pd.read_csv("upstairs 3.csv")
e3.insert(0, 'activity', "upstairs")
f3= pd.read_csv("downstairs 3.csv")
f3.insert(0, 'activity', "downstairs")
df3 = pd.concat([a3, b3, c3 , d3, e3 ,f3])
a4= pd.read_csv("sitting 4.csv")
a4.insert(0, 'activity', "sitting")
b4= pd.read_csv("standing 4.csv")
b4.insert(0, 'activity', "standing")
c4= pd.read_csv("walking 4.csv")
c4.insert(0, 'activity', "walking")
d4= pd.read_csv("jogging 4.csv")
d4.insert(0, 'activity', "jogging")
e4= pd.read_csv("upstairs 4.csv")
e4.insert(0, 'activity', "upstairs")
f4= pd.read_csv("downstairs 4.csv")
f4.insert(0, 'activity', "downstairs")
df4 = pd.concat([a4, b4, c4 , d4, e4 ,f4])
a5= pd.read_csv("sitting 5.csv")
a5.insert(0, 'activity', "sitting")
b5= pd.read_csv("standing 5.csv")
b5.insert(0, 'activity', "standing")
c5= pd.read_csv("walking 5.csv")
c5.insert(0, 'activity', "walking")
d5= pd.read_csv("jogging 5.csv")
d5.insert(0, 'activity', "jogging")
e5= pd.read_csv("upstairs 5.csv")
e5.insert(0, 'activity', "upstairs")
f5= pd.read_csv("downstairs 5.csv")
f5.insert(0, 'activity', "downstairs")
df5 = pd.concat([a5, b5, c5 , d5, e5 ,f5])
f_final = pd.concat([df1, df2, df3, df4, df5], axis=0)
df_final.columns = ["activity", "time 1", "accx", "accy", "accz", "time 2", "gyrx", "gyry",
"gyrz", "hr", "longitude", "latitude"]
df_final= df_final.drop(['time 1', 'time 2', "hr", "longitude", "latitude" ], axis = 1).copy()
df_final.dropna(how='any', inplace=True)
activities = df_final['activity'].value_counts().index
label = LabelEncoder()
df_final['label'] = label.fit_transform(df_final['activity'])
X = df_final[['accx', 'accy', 'accz', 'gyrx', 'gyry', 'gyrz']]
y = df_final['label']
scaler = StandardScaler()
X = scaler.fit_transform(X)
df_final = pd.DataFrame(X, columns = ['accx', 'accy', 'accz', 'gyrx', 'gyry', 'gyrz'])
df_final['label'] = y.values
Fs = 50
frame_size = Fs*2 # 200 samples
hop_size = frame_size # 40 samples
def get_frames(df_final, frame_size, hop_size):
N_FEATURES = 6 #x,y,z (acc,gut)
frames = []
labels = []
for i in range(0, len(df_final) - frame_size, hop_size):
accx = df_final['accx'].values[i: i + frame_size]
accy = df_final['accy'].values[i: i + frame_size]
accz = df_final['accz'].values[i: i + frame_size]
gyrx = df_final['gyrx'].values[i: i + frame_size]
gyry = df_final['gyry'].values[i: i + frame_size]
gyrz = df_final['gyrz'].values[i: i + frame_size]
# Retrieve the most often used label in this segment
label = stats.mode(df_final['label'][i: i + frame_size])[0][0]
frames.append([accx, accy, accz, gyrx, gyry, gyrz])
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(df_final, frame_size, hop_size)
pred = model.predict_classes(X)
if __name__ == '__main__':
app.run(host="localhost", port=8000, debug=False)
