ranpelta

# import packages
import pandas as pd
import numpy as np
import keras
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()
from keras.preprocessing.sequence import TimeseriesGenerator
from keras.models import Sequential

ranpelta

ranpelta

ranpelta

ranpelta

# import packages
import pandas as pd
import numpy as np
import keras
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()
from keras.preprocessing.sequence import TimeseriesGenerator
from keras.models import Sequential

ranpelta

df = pd.read_pickle(r'C:\..........\data.pkl') # read data 
y_col='y' # define y variable, i.e., what we want to predict
print(df.shape) # print the number of rows anc columns
df.head()

ranpelta

plt.figure(figsize=(50,4))
plt.plot(range(len(df)),df[y_col]);

ranpelta

test_size = int(len(df) * 0.1) # the test data will be 10% (0.1) of the entire data
train = df.iloc[:-test_size,:].copy() 
# the copy() here is important, it will prevent us from getting: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_index,col_indexer] = value instead
test = df.iloc[-test_size:,:].copy()
print(train.shape, test.shape)

>>> ((28916, 4), (3212, 4))

ranpelta

plt.figure(figsize=(50,4))
plt.plot(train.index,train[y_col],label='Train');
plt.plot(test.index,test[y_col],label='test')
plt.legend();

ranpelta

#separate X and y only for the train data (for now)
X_train = train.drop(y_col,axis=1).copy()
y_train = train[[y_col]].copy() # the double brakets here are to keep the y in a dataframe format, otherwise it will be pandas Series
print(X_train.shape, y_train.shape)

>>> (28916, 3) (28916, 1)