Jason42Jason42

Enrique_ds

Last updated: July 21st, 2019

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

%matplotlib inline

import warnings
warnings.filterwarnings('ignore')

In [2]:

consumption_df = pd.read_csv('consumption_monthly.csv', header=0, skiprows=4, na_values='.')

In [3]:

consumption_df['CONSUMPTION'] = consumption_df['CONSUMPTION'].str.replace(',', '')
consumption_df['CONSUMPTION'] = consumption_df['CONSUMPTION'].apply(int)

In [4]:

consumption_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3120 entries, 0 to 3119
Data columns (total 6 columns):
YEAR                3120 non-null int64
MONTH               3120 non-null int64
STATE               3120 non-null object
TYPE OF PRODUCER    3120 non-null object
ENERGY SOURCE       3120 non-null object
CONSUMPTION         3120 non-null int64
dtypes: int64(3), object(3)
memory usage: 146.3+ KB

In [5]:

consumption_df.head()

Out[5]:

	YEAR	MONTH	STATE	TYPE OF PRODUCER	ENERGY SOURCE	CONSUMPTION
0	2019	1	AK	Total Electric Power Industry	Coal (Short Tons)	59973
1	2019	1	AK	Total Electric Power Industry	Natural Gas (Mcf)	3414933
2	2019	1	AK	Total Electric Power Industry	Petroleum (Barrels)	157580
3	2019	1	AK	Combined Heat and Power, Industrial Power	Natural Gas (Mcf)	26836
4	2019	1	AK	Combined Heat and Power, Industrial Power	Petroleum (Barrels)	5093

In [8]:

states_df = consumption_df.groupby("STATE")["CONSUMPTION"].sum().sort_values(ascending=False).head(21).to_frame()
states_df = states_df.drop('US-Total')
states_df

Out[8]:

	CONSUMPTION
STATE
TX	946505908
FL	743289836
PA	388907950
CA	364914477
LA	306878816
VA	250479040
OH	240754220
AL	236636112
GA	232638274
NY	212024376
NC	200045190
MS	199050032
AZ	189270550
OK	178081988
NJ	168271768
MI	160875665
IN	153771462
NV	106820425
WI	105814706
IL	105686016

In [9]:

ax = states_df.plot(kind='bar', title ="Per State Consumption",figsize=(15,10),legend=True, fontsize=12)
ax.set_xlabel("State",fontsize=12)
ax.set_ylabel("Consumption",fontsize=12)

Out[9]:

Text(0,0.5,'Consumption')

In [10]:

producer_df = consumption_df.groupby("TYPE OF PRODUCER")["CONSUMPTION"].sum().sort_values(ascending=False)
producer_df

Out[10]:

TYPE OF PRODUCER
Total Electric Power Industry                       6768022461
Electric Generators, Electric Utilities             3500315607
Electric Generators, Independent Power Producers    2380385395
Combined Heat and Power, Electric Power              483778096
Combined Heat and Power, Industrial Power            369631109
Combined Heat and Power, Commercial Power             33912252
Name: CONSUMPTION, dtype: int64

In [11]:

ax = producer_df.plot(kind='bar', title ="Consumption by Producer Type",figsize=(15,10),legend=True, fontsize=12)
ax.set_xlabel("Type of Producer",fontsize=12)
ax.set_ylabel("Consumption",fontsize=12)

Out[11]:

Text(0,0.5,'Consumption')

In [12]:

energy_df = consumption_df.groupby("ENERGY SOURCE")["CONSUMPTION"].sum().sort_values(ascending=False)
energy_df

Out[12]:

ENERGY SOURCE
Natural Gas (Mcf)            12777921288
Coal (Short Tons)              712450668
Petroleum (Barrels)             45374859
Geothermal (Billion Btu)          205972
Other Gases (Billion Btu)          92133
Name: CONSUMPTION, dtype: int64

In [13]:

ax = energy_df.plot(kind='bar', title ="Consumption by Energy Source",figsize=(15,10),legend=True, fontsize=12)
ax.set_xlabel("Energy Source",fontsize=12)
ax.set_ylabel("Consumption",fontsize=12)

Out[13]:

Text(0,0.5,'Consumption')