Ejemplo n.º 1
0
                #   Attach proper audio file name to file path
                wav_file_path = os.path.join(file_dir, file)
                file_array.append(wav_file_path)
                try:
                    #   Read the audio file
                    afile, sample_rate = load(wav_file_path)
                    #   Get the average mel function of the audio files
                    mfcc_a = mfcc(y=audio_array, sr=sample_rate, n_mfcc=40)
                    mfcc_mean = np.mean(mfcc_a.T, axis=0)
                except Exception as e:
                    print("Error encountered while parsing file: ", file_dir)
                    return None, None

                feature = mfcc_mean
                label = str(os.path.splitext(file_dir)[0])

                return [feature, label]


parser()

temp = train.apply(parser, axis=1)
temp.columns = ['feature', 'label']

X = np.array(temp.feature.to_list())
y = np.array(temp.feature.to_list())

lb = LabelEncoder()

y = np_utils.to_categorical(lb.fit_tranform(y))
Ejemplo n.º 2
0
df.isnull().sum()

# In[27]:

df.drop("Embarked", axis=1, inplace=True)

# In[30]:

df["Age"].hist(bins=4)

# we can observe that there most of the people on ship are in age group of 20 to 40.

# In[31]:

le = LabelEncoder()
df["Sex"] = le.fit_tranform(df["Age"])

# In[38]:

from sklearn.preprocessing import LabelEncoder

# In[43]:

le = LabelEncoder()
df_new = le.fit_transform(df["Sex"])

# In[34]:

df["Sex"]

# In[35]: