import matplotlib.pyplot as plt
import pandas as pd
import keras
titles = [
“Pressure”,
“Temperature”,
“Temperature in Kelvin”,
“Temperature (dew point)”,
“Relative Humidity”,
“Saturation vapor pressure”,
“Vapor pressure”,
“Vapor pressure deficit”,
“Specific humidity”,
“Water vapor concentration”,
“Airtight”,
“Wind speed”,
“Maximum wind speed”,
“Wind direction in degrees”,
]
feature_keys = [
“p (mbar)”,
“T (degC)”,
“Tpot (K)”,
“Tdew (degC)”,
“rh (%)”,
“VPmax (mbar)”,
“VPact (mbar)”,
“VPdef (mbar)”,
“sh (g/kg)”,
“H2OC (mmol/mol)”,
“rho (g/m**3)”,
“wv (m/s)”,
“max. wv (m/s)”,
“wd (deg)”,
]
colors = [
“blue”,
“orange”,
“green”,
“red”,
“purple”,
“brown”,
“pink”,
“gray”,
“olive”,
“cyan”,
]
date_time_key = “Date Time”
def show_raw_visualization(data):
time_data = data[date_time_key]
fig, axes = plt.subplots(
nrows=7, ncols=2, figsize=(15, 20), dpi=80, facecolor=”w”, edgecolor=”k”
)
for i in range(len(feature_keys)):
key = feature_keys[i]
c = colors[i % (len(colors))]
t_data = data[key]
t_data.index = time_data
t_data.head()
ax = t_data.plot(
ax=axes[i // 2, i % 2],
color=c,
title=”{} – {}”.format(titles[i], key),
rot=25,
)
ax.legend([titles[i]])
plt.tight_layout()
df = pd.read_csv(‘data/timeseries/climate.csv’)
show_raw_visualization(df)
# plt.show()
split_fraction = 0.715
train_split = int(split_fraction * int(df.shape[0]))
step = 6
past = 720
future = 72
learning_rate = 0.001
batch_size = 256
epochs = 10
def normalize(data, train_split):
data_mean = data[:train_split].mean(axis=0)
data_std = data[:train_split].std(axis=0)
return (data – data_mean) / data_std
selected_features = [feature_keys[i] for i in [0, 1, 5, 7, 8, 10, 11]]
features = df[selected_features]
features.index = df[date_time_key]
features.head()
features = normalize(features.values, train_split)
features = pd.DataFrame(features)
features.head()
train_data = features.loc[0:train_split – 1]
val_data = features.loc[train_split:]
start = past + future
end = start + train_split
x_train = train_data[[i for i in range(7)]].values
y_train = features.iloc[start:end][[1]]
sequence_length = int(past / step)
dataset_train = keras.preprocessing.timeseries_dataset_from_array(
x_train,
y_train,
sequence_length=sequence_length,
sampling_rate=step,
batch_size=batch_size,)
x_end = len(val_data) – past – future
label_start = train_split + past + future
x_val = val_data.iloc[:x_end][[i for i in range(7)]].values
y_val = features.iloc[label_start:][[1]]
dataset_val = keras.preprocessing.timeseries_dataset_from_array(
x_val,
y_val,
sequence_length=sequence_length,
sampling_rate=step,
batch_size=batch_size,)
for batch in dataset_train.take(1):
inputs, targets = batch
print(“Input shape:”, inputs.numpy().shape)
print(“Target shape:”, targets.numpy().shape)
inputs = keras.layers.Input(shape=(inputs.shape[1], inputs.shape[2]))
lstm_out = keras.layers.LSTM(32)(inputs)
outputs = keras.layers.Dense(1)(lstm_out)
model = keras.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer=keras.optimizers.Adam(
learning_rate=learning_rate), loss=”mse”)
model.summary()
path_checkpoint = “model_checkpoint.weights.h5”
es_callback = keras.callbacks.EarlyStopping(
monitor=”val_loss”, min_delta=0, patience=5)
modelckpt_callback = keras.callbacks.ModelCheckpoint(
monitor=”val_loss”,
filepath=path_checkpoint,
verbose=1,
save_weights_only=True,
save_best_only=True,
)
history = model.fit(
dataset_train,
epochs=epochs,
validation_data=dataset_val,
callbacks=[es_callback, modelckpt_callback],
)
def visualize_loss(history, title):
loss = history.history[“loss”]
val_loss = history.history[“val_loss”]
epochs = range(len(loss))
plt.figure()
plt.plot(epochs, loss, “b”, label=”Training loss”)
plt.plot(epochs, val_loss, “r”, label=”Validation loss”)
plt.title(title)
plt.xlabel(“Epochs”)
plt.ylabel(“Loss”)
plt.legend()
plt.show()
visualize_loss(history, “Training and Validation Loss”)
source: https://keras.io/
You need to login in order to like this post: click here
YOU MIGHT ALSO LIKE
SUBSCRIBE TO OUR NEWSLETTER
