Reputation: 1
I'm trying to convert my data frame to a tensor.
df_1 = pd.read_csv(r'data/flight_data_set/flight.csv',
usecols= ['Airline name ', 'Travel Time' ,'Number of Stoppage ', 'Depreture Airport', 'Depreture Time', '1st Stoppage Waiting Hour', '1st Stoppage', '2nd StoppageWaiting Time'])
train_x = torch.tensor(df_1.values)
I tried to change the array to a tensor, but it threw the error :
can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16
Upvotes: 0
Views: 150
Reputation: 1461
Because you have many string variables. You cant introduce strings to a NN. You need to tranform them to numbers first.
Upvotes: 0