# 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))
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]:
