[datetime]S7_05_Practical_example3

Avocado.csv

0.83MB

 

 

In [68]:

import pandas as pd
import datetime as dt

 

In [69]:

avo_df = pd.read_csv('Avocado.csv')
avo_df

 

Out[69]:

	Date	AveragePrice	Total Volume	type	region
0	2015-12-27	1.33	64236.62	conventional	Albany
1	2015-12-20	1.35	54876.98	conventional	Albany
2	2015-12-13	0.93	118220.22	conventional	Albany
3	2015-12-06	1.08	78992.15	conventional	Albany
4	2015-11-29	1.28	51039.60	conventional	Albany
...	...	...	...	...	...
18244	2018-02-04	1.63	17074.83	organic	WestTexNewMexico
18245	2018-01-28	1.71	13888.04	organic	WestTexNewMexico
18246	2018-01-21	1.87	13766.76	organic	WestTexNewMexico
18247	2018-01-14	1.93	16205.22	organic	WestTexNewMexico
18248	2018-01-07	1.62	17489.58	organic	WestTexNewMexico

18249 rows × 5 columns

 

In [70]:

avo_df['Date'] = pd.to_datetime(avo_df['Date'])
avo_df.set_index(keys=['Date'], inplace = True)
avo_df

 

Out[70]:

	AveragePrice	Total Volume	type	region
Date
2015-12-27	1.33	64236.62	conventional	Albany
2015-12-20	1.35	54876.98	conventional	Albany
2015-12-13	0.93	118220.22	conventional	Albany
2015-12-06	1.08	78992.15	conventional	Albany
2015-11-29	1.28	51039.60	conventional	Albany
...	...	...	...	...
2018-02-04	1.63	17074.83	organic	WestTexNewMexico
2018-01-28	1.71	13888.04	organic	WestTexNewMexico
2018-01-21	1.87	13766.76	organic	WestTexNewMexico
2018-01-14	1.93	16205.22	organic	WestTexNewMexico
2018-01-07	1.62	17489.58	organic	WestTexNewMexico

18249 rows × 4 columns

 

In [92]:

# Aggregating the data by month
avo_df.resample(rule='M').mean()

 

Out[92]:

	AveragePrice	Total Volume	Day	Month	Year
Date
2015-01-31	1.341444	8.102564e+05	17.800000	1.0	2015.0
2015-02-28	1.353580	7.505690e+05	14.000000	2.0	2015.0
2015-03-31	1.361981	7.751538e+05	15.000000	3.0	2015.0
2015-04-30	1.383449	7.966305e+05	15.500000	4.0	2015.0
2015-05-31	1.344685	8.958964e+05	17.000000	5.0	2015.0
2015-06-30	1.399074	8.838582e+05	17.500000	6.0	2015.0
2015-07-31	1.409444	8.256988e+05	15.500000	7.0	2015.0
2015-08-31	1.444481	7.763793e+05	16.000000	8.0	2015.0
2015-09-30	1.449144	7.620806e+05	16.500000	9.0	2015.0
2015-10-31	1.391968	7.078151e+05	14.500000	10.0	2015.0
2015-11-30	1.330611	6.841482e+05	15.000000	11.0	2015.0
2015-12-31	1.305244	6.868351e+05	16.524362	12.0	2015.0
2016-01-31	1.236991	8.828596e+05	13.500000	1.0	2016.0
2016-02-29	1.240278	9.678819e+05	15.000000	2.0	2016.0
2016-03-31	1.224213	9.055843e+05	16.500000	3.0	2016.0
2016-04-30	1.205023	9.301684e+05	13.500000	4.0	2016.0
2016-05-31	1.199722	1.039316e+06	15.000000	5.0	2016.0
2016-06-30	1.283056	9.498337e+05	15.500000	6.0	2016.0
2016-07-31	1.401333	8.653247e+05	17.000000	7.0	2016.0
2016-08-31	1.411111	8.583263e+05	17.500000	8.0	2016.0
2016-09-30	1.427870	8.386650e+05	14.500000	9.0	2016.0
2016-10-31	1.557093	6.670404e+05	16.000000	10.0	2016.0
2016-11-30	1.550023	6.023364e+05	16.500000	11.0	2016.0
2016-12-31	1.315995	7.672402e+05	14.500000	12.0	2016.0
2017-01-31	1.277500	9.876538e+05	15.000000	1.0	2017.0
2017-02-28	1.214792	1.091359e+06	15.500000	2.0	2017.0
2017-03-31	1.398935	8.307949e+05	15.500000	3.0	2017.0
2017-04-30	1.502611	9.070639e+05	16.000000	4.0	2017.0
2017-05-31	1.532593	9.854874e+05	17.500000	5.0	2017.0
2017-06-30	1.545395	9.544434e+05	14.467442	6.0	2017.0
2017-07-31	1.564926	8.794513e+05	16.000000	7.0	2017.0
2017-08-31	1.698958	7.831782e+05	16.500000	8.0	2017.0
2017-09-30	1.840949	6.592119e+05	13.500000	9.0	2017.0
2017-10-31	1.752444	6.718110e+05	15.000000	10.0	2017.0
2017-11-30	1.517292	7.512021e+05	15.500000	11.0	2017.0
2017-12-31	1.363852	8.506164e+05	17.000000	12.0	2017.0
2018-01-31	1.387431	9.946923e+05	17.500000	1.0	2018.0
2018-02-28	1.318704	1.152264e+06	14.500000	2.0	2018.0
2018-03-31	1.336458	1.053827e+06	14.500000	3.0	2018.0

 

In [93]:

import matplotlib.pyplot as plt

 

In [96]:

# average price per month
avo_df.resample(rule='M').mean()['AveragePrice'].plot(figsize=(10,5), marker='o', color = 'b')

 

Out[96]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fe21ab8b340>

 

 

In [95]:

# average price per quarter
avo_df.resample(rule='Q').mean()['AveragePrice'].plot(figsize=(10,5), marker='o', color = 'g')

 

Out[95]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fe21b475220>

 

 

In [97]:

# average price per annual
avo_df.resample(rule='A').mean()['AveragePrice'].plot(figsize=(10,5), marker='o', color = 'k')

 

Out[97]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fe21ab6ca00>

 

 

In [98]:

import seaborn as sns

 

In [99]:

plt.figure(figsize=(20,10))
sns.violinplot(y='AveragePrice', x='type', data = avo_df)

 

Out[99]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fe212e686a0>

 

 

In [101]:

plt.figure(figsize=(15,8))
sns.distplot(avo_df['AveragePrice'], color='b')

 

 

/usr/local/lib/python3.8/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

Out[101]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fe20e4eaee0>

 

 

In [102]:

# categorical plots onto a FacetGrid
# show the relationship between a numerical and categorical variables
# obtain a lot of information from catplot
conventional = sns.catplot('AveragePrice', 'region', data = avo_df[avo_df['type']=='conventional'],hue = 'Year', height =10 )

 

 

/usr/local/lib/python3.8/dist-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(