timeSeries_debug.py

import os
import datetime

import IPython
import IPython.display
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
import tensorflow as tf
import _utils as ut

'''
Convolutional and Recurrent Neural Networks (CNNs and RNNs).

Forecast for a single timestep:
    A single feature.
    All features.
Forecast multiple steps:
    Single-shot: Make the predictions all at once.
    Autoregressive: Make one prediction at a time and feed the output back to the model.
'''

mpl.rcParams['figure.figsize'] = (8, 6)
mpl.rcParams['axes.grid'] = False

#  weather time series dataset recorded by the Max Planck Institute for Biogeochemistry.
zip_path = tf.keras.utils.get_file(
    origin='https://storage.googleapis.com/tensorflow/tf-keras-datasets/jena_climate_2009_2016.csv.zip',
    fname='jena_climate_2009_2016.csv.zip',
    extract=True)
csv_path, _ = os.path.splitext(zip_path)

df = pd.read_csv(csv_path)
# slice [start:stop:step], starting from index 5 take every 6th record.
df = df[5::6]

# sub-sampling the data from 10 minute intervals to 1h
date_time = pd.to_datetime(df.pop('Date Time'), format='%d.%m.%Y %H:%M:%S')

# first results from dataset already loaded
print(df.head())

print(ut.bcolors.ENDLINE)

#PLOT
#  few features over time
plot_cols = ['T (degC)', 'p (mbar)', 'rho (g/m**3)']
plot_features = df[plot_cols]
plot_features.index = date_time
_ = plot_features.plot(subplots=True)

plot_features = df[plot_cols][:480]
plot_features.index = date_time[:480]
_ = plot_features.plot(subplots=True)

# Inspect and cleanup
'''
df.describe().transpose()

wv = df['wv (m/s)']
bad_wv = wv == -9999.0
wv[bad_wv] = 0.0

max_wv = df['max. wv (m/s)']
bad_max_wv = max_wv == -9999.0
max_wv[bad_max_wv] = 0.0

# The above inplace edits are reflected in the DataFrame
df['wv (m/s)'].min()


'''