forecast.py

#!/usr/bin/env python
# coding: utf-8

import sklearn
from tsai.basics import *
#my_setup(sklearn)

import pandas as pd
df=pd.read_csv('D:/project/aircompressordata.csv')
df=df.drop(['data_id','ideal_specific_power_kw_100cfm','device_id'],axis=1)
print(df.columns)
df.head(5)


# In[3]:


datetime_col="timestamp"
freq='1H'
coloumns=df.columns[:7]
method='ffill'
value=0

preproc_pipe=sklearn.pipeline.Pipeline([
    ('shrinker',TSShrinkDataFrame()),
    ('drop_duplicates',TSDropDuplicates(datetime_col=datetime_col)),
    ('add_mts',TSAddMissingTimestamps(datetime_col=datetime_col,freq=freq)),
    ('fill_missing',TSFillMissing(columns=coloumns,method=method,value=value)),
    ],
    verbose=True)
mkdir('data', exist_ok=True,parents=True)
save_object(preproc_pipe,'data/preproc_pipe.pkl')
preproc_pipe=load_object('data/preproc_pipe.pkl')

df=preproc_pipe.fit_transform(df)


# In[4]:


df.head()


# In[5]:


fcst_history=200
fcst_horizon=72
valid_size=0.1
test_size=0.2

splits=get_forecasting_splits(df,fcst_history=fcst_history,fcst_horizon=fcst_horizon,datetime_col=datetime_col,
                              valid_size=valid_size,test_size=test_size)

splits


# In[6]:


coloumns=df.columns[1:]
train_split=splits[0]

exp_pipe=sklearn.pipeline.Pipeline([
    ('scaler',TSStandardScaler(columns=coloumns)),
    ],
    verbose=True)

save_object(exp_pipe,'data/exp_pipe.pkl')
exp_pipe=load_object('data/exp_pipe.pkl')

df_scaled=exp_pipe.fit_transform(df,scaler__idxs=train_split)

df_scaled


# In[7]:


x_vars=df.columns[1:]
y_vars=df.columns[1:]


# In[8]:


X,y=prepare_forecasting_data(df,fcst_history=fcst_history,fcst_horizon=fcst_horizon,x_vars=x_vars,y_vars=y_vars)
X.shape , y.shape


# In[9]:


arch_config=dict(
    n_layers=3,
    n_heads=4,
    d_model=16,
    d_ff=128,
    attn_dropout=0.0,
    dropout=0.3,
    patch_len=24,
    stride=2,
    padding_patch=True,
)


# In[10]:


learn=TSForecaster(X,y,splits=splits,
                   batch_size=16,path="models",
                   pipelines=[preproc_pipe,exp_pipe],
                   arch="PatchTST",
                   arch_config=arch_config,
                   metrics=[mse,mae],
                   cbs=ShowGraph())


# In[11]:


learn.summary()


# In[12]:


lr_max=learn.lr_find().valley


# In[ ]:


n_epochs=100

learn.fit_one_cycle(n_epoch=n_epochs,lr_max=lr_max)
learn.export('PatchTST.pt')


# In[14]:


from tsai.inference import load_learner
from sklearn.metrics import mean_squared_error, mean_absolute_error
from sklearn.metrics import mean_absolute_percentage_error

learn=load_learner('models/PatchTST.pt')
y_test_preds, *_=learn.get_X_preds(X[splits[2]])
y_test_preds=to_np(y_test_preds)
print(y_test_preds.shape)

y_test=y[splits[2]]

print(mean_squared_error(y_test.flatten(),y_test_preds.flatten()))
print(mean_absolute_error(y_test.flatten(),y_test_preds.flatten()))
print(mean_absolute_percentage_error(y_test.flatten(),y_test_preds.flatten()))


# In[15]:


X_test=X[splits[2]]
plot_forecast(X_test,y_test,y_test_preds,sel_vars=True)


# In[16]:


fcst_date="2023-07-31 23:00:00"
dates=pd.date_range(start=None,end=fcst_date,periods=fcst_history,freq=freq)
dates


# In[17]:


#df=pd.read_csv('D:/project/aircompressordata.csv')
#df=preproc_pipe.fit_transform(df)

new_df=df[df[datetime_col].isin(dates)].reset_index(drop=True)
new_df


# In[18]:


from tsai.inference import load_learner

predict=load_learner('models/PatchTST.pt')
new_df=predict.transform(new_df)

new_df


# In[19]:


x_feat=new_df.columns[1:]
new_x,__=prepare_forecasting_data(new_df,fcst_history=fcst_history,fcst_horizon=0,x_vars=x_vars,y_vars=y_vars)
new_x.shape


# In[20]:


new_scaled_preds, *_ = learn.get_X_preds(new_x)

new_scaled_preds=to_np(new_scaled_preds).swapaxes(1,2).reshape(-1,len(y_vars))
dates=pd.date_range(start=fcst_date, periods=fcst_horizon+1,freq='1H')[1:]
preds_df=pd.DataFrame(dates,columns=[datetime_col])
preds_df.loc[:, y_vars]=new_scaled_preds
preds_df=learn.inverse_transform(preds_df)

preds_df


# In[1]:


from tsai.export import get_nb_name; nb_name=get_nb_name(locals())
from tsai.imports import  create_scripts; create_scripts(nb_name)


# In[ ]: