bkaankuguoglu

#=======================================================================#
# pdf_utils.py                                                          #
#=======================================================================#
# usage: pdf_utils.py [-h] [-i INPUT_DIR] [-o OUTPUT_DIR] [-m METHOD]
#
# This program contains some utility functions for pdf files.
#
# optional arguments:
#  -h, --help            show this help message and exit
#  -i INPUT_DIR, --input_dir INPUT_DIR

bkaankuguoglu

#=======================================================================#
# extract_data.py                                                       #
#=======================================================================#
# usage: extract_data.py [-h] [-i INPUT_DIR] [-o OUTPUT_DIR]
#
# This program extracts provision numbers from a set of documents.
#
# optional arguments:
#  -h, --help            show this help message and exit
#  -i INPUT_DIR, --input_dir INPUT_DIR

bkaankuguoglu

#========================================================================#
# file_collector.py                                                      #
#========================================================================#
#========================================================================#
# usage: file_collector.py [-h] [-f FILE] [-o OUTPUT_FOLDER]             #
#========================================================================#
# optional arguments:
#  -h, --help            show this help message and exit
#  -f FILE, --file FILE  the xlsx file that contains all the files to be
#                        collected

bkaankuguoglu

import plotly.graph_objs as go
from plotly.offline import iplot

def plot_dataset(df, title):
    data = []
    value = go.Scatter(
        x=df.index,
        y=df.value,
        mode="lines",
        name="values",

bkaankuguoglu

import pandas as pd

df = pd.read_csv('<YOUR_FILE_DIR>/PJME_hourly.csv')

df = df.set_index(['Datetime'])
df.index = pd.to_datetime(df.index)
if not df.index.is_monotonic:
    df = df.sort_index()
    
df = df.rename(columns={'PJME_MW': 'value'})

bkaankuguoglu

def generate_time_lags(df, n_lags):
    df_n = df.copy()
    for n in range(1, n_lags + 1):
        df_n[f"lag{n}"] = df_n["value"].shift(n)
    df_n = df_n.iloc[n_lags:]
    return df_n
    
input_dim = 100

df_generated = generate_time_lags(df, input_dim)

bkaankuguoglu

from sklearn.model_selection import train_test_split

def feature_label_split(df, target_col):
    y = df[[target_col]]
    X = df.drop(columns=[target_col])
    return X, y

def train_val_test_split(df, target_col, test_ratio):
    val_ratio = test_ratio / (1 - test_ratio)
    X, y = feature_label_split(df, target_col)

bkaankuguoglu

from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler()
X_train_arr = scaler.fit_transform(X_train)
X_val_arr = scaler.transform(X_val)
X_test_arr = scaler.transform(X_test)

y_train_arr = scaler.fit_transform(y_train)
y_val_arr = scaler.transform(y_val)
y_test_arr = scaler.transform(y_test)

bkaankuguoglu

from torch.utils.data import TensorDataset, DataLoader

batch_size = 64

train_features = torch.Tensor(X_train_arr)
train_targets = torch.Tensor(y_train_arr)
val_features = torch.Tensor(X_val_arr)
val_targets = torch.Tensor(y_val_arr)
test_features = torch.Tensor(X_test_arr)
test_targets = torch.Tensor(y_test_arr)

bkaankuguoglu

class RNNModel(nn.Module):
    def __init__(self, input_dim, hidden_dim, layer_dim, output_dim, dropout_prob):
        super(RNNModel, self).__init__()

        # Defining the number of layers and the nodes in each layer
        self.hidden_dim = hidden_dim
        self.layer_dim = layer_dim

        # RNN layers
        self.rnn = nn.RNN(