2017-04-17-slopes.ipynb

Kernel: Python 3 (Anaconda)

import pandas as pd
import numpy as np

netatmo = pd.read_csv('NetAtmo_2016.csv', parse_dates=True, index_col=1)

%matplotlib inline
netatmo['CO2'].plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f0c9a720588>

delta_CO2 = netatmo['CO2'].diff(1)

# calculate difference between time samples in seconds
netatmo['time'] = netatmo.index
delta_time = netatmo['time'].diff(1) / np.timedelta64(1,'s')
slopes = delta_CO2 / delta_time

# slopes in units of ppm per second
%matplotlib inline
#(delta_CO2.values / delta_time).plot()
slopes.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f0c9a23e0f0>

slopes.describe()

count    9.013100e+04
mean              NaN
std               NaN
min              -inf
25%     -2.000000e-02
50%      0.000000e+00
75%      1.666667e-02
max               inf
dtype: float64

neg_slopes = slopes[slopes<0]

yearsdecay = (neg_slopes * netatmo['CO2'])
(yearsdecay).plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f0c9a25a2b0>

yearsdecay.to_csv('ETC-Weather-2016.csv')
year1= pd.read_csv('ETC-Weather-2016.csv', parse_dates=True, index_col=1)

year1.dtypes

2016-02-19 13:26:00    object
dtype: object

year1.head()

	2016-02-19 13:26:00
NaN	2016-02-19 13:27:00
NaN	2016-02-19 13:27:00
NaN	2016-02-19 13:31:00
-5.533333	2016-02-19 13:36:00
-4.373333	2016-02-19 13:41:00

year1.describe()

	2016-02-19 13:26:00
count	90148
unique	90126
top	2016-03-03 04:47:00
freq	4

year1.hist(bins=20)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-16-4fa8fb5997c0> in <module>()
----> 1 year1.hist(bins=20)

/ext/anaconda3/lib/python3.5/site-packages/pandas/plotting/_core.py in hist_frame(data, column, by, grid, xlabelsize, xrot, ylabelsize, yrot, ax, sharex, sharey, figsize, layout, bins, **kwds)
   2176     fig, axes = _subplots(naxes=naxes, ax=ax, squeeze=False,
   2177                           sharex=sharex, sharey=sharey, figsize=figsize,
-> 2178                           layout=layout)
   2179     _axes = _flatten(axes)
   2180 
/ext/anaconda3/lib/python3.5/site-packages/pandas/plotting/_tools.py in _subplots(naxes, sharex, sharey, squeeze, subplot_kw, ax, layout, layout_type, **fig_kw)
    235 
    236     # Create first subplot separately, so we can share it if requested
--> 237     ax0 = fig.add_subplot(nrows, ncols, 1, **subplot_kw)
    238 
    239     if sharex:
/ext/anaconda3/lib/python3.5/site-packages/matplotlib/figure.py in add_subplot(self, *args, **kwargs)
   1072                     self._axstack.remove(ax)
   1073 
-> 1074             a = subplot_class_factory(projection_class)(self, *args, **kwargs)
   1075 
   1076         self._axstack.add(key, a)
/ext/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_subplots.py in __init__(self, fig, *args, **kwargs)
     62                     raise ValueError(
     63                         "num must be 1 <= num <= {maxn}, not {num}".format(
---> 64                             maxn=rows*cols, num=num))
     65                 self._subplotspec = GridSpec(rows, cols)[int(num) - 1]
     66                 # num - 1 for converting from MATLAB to python indexing
ValueError: num must be 1 <= num <= 0, not 1

<matplotlib.figure.Figure at 0x7f0c94971cc0>

data = pd.read_csv('NetAtmo_2016.csv', parse_dates=True, index_col=1)

data.head()

data.dtypes

data['Timestamp'] = data.index

data.index

start_time = '2016-11-19 13:26:00'
end_time = '2016-12-31 23:55:00'
date_range = (data['Timestamp'] >= start_time) & (data['Timestamp'] <= end_time)

%matplotlib inline
data.loc[date_range].plot()

data['2016-02-19 13:26':'2016-02-19 13:32']['Timestamp'].diff(1)

data.loc[date_range] = data_range
data_range ['CO2']

data.loc[date_range]

%matplotlib inline
(delta_CO2.values / delta_time).plot()

data.head()