import pandas as pd
df=pd.read_csv('nyc_taxis.csv', sep=',',header=None)
print(df.head(2))
ndarray = df.to_numpy()
print(ndarray[:2,:])
0 1 2 3 4 \
0 pickup_year pickup_month pickup_day pickup_dayofweek pickup_time
1 2016 1 1 5 0
5 6 7 8 \
0 pickup_location_code dropoff_location_code trip_distance trip_length
1 2 4 21.00 2037
9 10 11 12 13 \
0 fare_amount fees_amount tolls_amount tip_amount total_amount
1 52.0 0.8 5.54 11.65 69.99
14
0 payment_type
1 1
[['pickup_year' 'pickup_month' 'pickup_day' 'pickup_dayofweek'
'pickup_time' 'pickup_location_code' 'dropoff_location_code'
'trip_distance' 'trip_length' 'fare_amount' 'fees_amount'
'tolls_amount' 'tip_amount' 'total_amount' 'payment_type']
['2016' '1' '1' '5' '0' '2' '4' '21.00' '2037' '52.0' '0.8' '5.54'
'11.65' '69.99' '1']]
from numpy import genfromtxt
my_data = genfromtxt('nyc_taxis.csv', delimiter=',')
print(my_data[:2,:])
[[ nan nan nan nan nan nan nan
nan nan nan nan nan nan nan
nan]
[2.016e+03 1.000e+00 1.000e+00 5.000e+00 0.000e+00 2.000e+00 4.000e+00
2.100e+01 2.037e+03 5.200e+01 8.000e-01 5.540e+00 1.165e+01 6.999e+01
1.000e+00]]
import csv
import numpy as np
# import nyc_taxi.csv as a list of lists
f = open("nyc_taxis.csv", "r")
taxi_list = list(csv.reader(f))
# remove the header row
taxi_list = taxi_list[1:]
# convert all values to floats
converted_taxi_list = []
for row in taxi_list:
converted_row = []
for item in row:
converted_row.append(float(item))
converted_taxi_list.append(converted_row)
taxi = np.array(converted_taxi_list, dtype=object)
print(taxi.shape)
print(taxi[:2,:])
(5, 15) [[2016.0 1.0 1.0 5.0 0.0 2.0 4.0 21.0 2037.0 52.0 0.8 5.54 11.65 69.99 1.0] [2016.0 1.0 1.0 5.0 0.0 2.0 1.0 16.29 1520.0 45.0 1.3 0.0 8.0 54.3 1.0]]
import pandas as pd
data = pd.read_csv("nyc_taxis.csv")
store = pd.HDFStore('dataset.h5')
store['mydata'] = data
store.close()
store = pd.HDFStore('dataset.h5')
data = store['mydata']
store.close()
print(type(data))
#data to numpy format
data = data.values
print(type(data))
<class 'pandas.core.frame.DataFrame'> <class 'numpy.ndarray'>
import pandas as pd
from numpy.random import randn
bar = pd.DataFrame(randn(10, 4))
store = pd.HDFStore('test.h5')
store['foo'] = bar # write to HDF5
bar = store['foo'] # retrieve
store.close()