I try to excute this code and I get the error bellow, I get the error in the random function and I don't know how to fix it, please help me.

def load_data(sample_split=0.3, usage='Training', to_cat=True, verbose=True,classes=['Angry','Happy'], filepath='C:/Users/Oussama/Desktop/fer2013.csv'):df = pd.read_csv(filepath)# print df.tail()# print df.Usage.value_counts()df = df[df.Usage == usage]frames = []classes.append('Disgust')for _class in classes:class_df = df[df['emotion'] == emotion[_class]]frames.append(class_df)data = pd.concat(frames, axis=0)rows = random.sample(data.index, int(len(data)*sample_split))data = data.ix[rows]print ('{} set for {}: {}'.format(usage, classes, data.shape))data['pixels'] = data.pixels.apply(lambda x: reconstruct(x))x = np.array([mat for mat in data.pixels]) # (n_samples, img_width, img_height)X_train = x.reshape(-1, 1, x.shape[1], x.shape[2])y_train, new_dict = emotion_count(data.emotion, classes, verbose)print (new_dict)if to_cat:y_train = to_categorical(y_train)return X_train, y_train, new_dict

I get this:

Traceback (most recent call last):File "fer2013datagen.py", line 71, in <module>verbose=True)File "fer2013datagen.py", line 47, in load_datarows = random.sample(data, int(len(data)*sample_split))File"C:\Users\Oussama\AppData\Local\Programs\Python\Python35\lib\random.py",line 311, in sampleraise TypeError("Population must be a sequence or set.  For dicts, uselist(d).")
TypeError: Population must be a sequence or set.  For dicts, use list(d).

Your code here:

rows = random.sample(data.index, int(len(data)*sample_split))

But, error message shows

rows = random.sample(data, int(len(data)*sample_split))

Why different? Did you modify it? And what is the type of data is? is it a list? or a dict?

And, error message has already told you how to fix it. it means the first parameter of random.sample must be a sequence or set. For dicts, use list(Dict).

For example,

d = {'a':1,'b':2}
random.sample(list(d), 1)

instead of

random.sample(d, 1)