베이징 공기 상태 데이터
BeijingRaw.csv
전처리 코드 ===============================
from pandas import read_csv
from datetime import datetime
# load data
def parse(x):
return datetime.strptime(x, '%Y %m %d %H')
dataset = read_csv('BeijingRaw.csv', parse_dates = [['year', 'month', 'day', 'hour']], index_col=0, date_parser=parse)
dataset.drop('No', axis=1, inplace=True)
# manually specify column names
dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']
dataset.index.name = 'date'
# mark all NA values with 0
dataset['pollution'].fillna(0, inplace=True)
# drop the first 24 hours
dataset = dataset[24:]
# summarize first 5 rows
print(dataset.head(5))
# save to file
dataset.to_csv('BeijingPollution.csv')
전처리 후 데이터 가시화 ========================
from pandas import read_csv
from matplotlib import pyplot
# load dataset
dataset = read_csv('BeijingPollution.csv', header=0, index_col=0)
values = dataset.values
# specify columns to plot
groups = [0, 1, 2, 3, 5, 6, 7]
i = 1
# plot each column
pyplot.figure()
for group in groups:
pyplot.subplot(len(groups), 1, i)
pyplot.plot(values[:, group])
pyplot.title(dataset.columns[group], y=0.5, loc='right')
i += 1
pyplot.show()
conversion to supervised data ====================
# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
n_vars = 1 if type(data) is list else data.shape[1]
df = DataFrame(data)
cols, names = list(), list()
# input sequence (t-n, ... t-1)
for i in range(n_in, 0, -1):
cols.append(df.shift(i))
names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
# forecast sequence (t, t+1, ... t+n)
for i in range(0, n_out):
cols.append(df.shift(-i))
if i == 0:
names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
else:
names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
# put it all together
agg = concat(cols, axis=1)
agg.columns = names
# drop rows with NaN values
if dropnan:
agg.dropna(inplace=True)
return agg
# load dataset
dataset = read_csv('BeijingPollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# frame as supervised learning
reframed = series_to_supervised(scaled, 1, 1)
# drop columns we don't want to predict
reframed.drop(reframed.columns[[9,10,11,12,13,14,15]], axis=1, inplace=True)
print(reframed.head())