I am running into an issue. The ReportDate field is something that comes with the csv pull but that is not what I want used on the X-axis. I want DataDate = ReportDate - 1
I am getting the following error:
I am getting the following error:
Error:Traceback (most recent call last):
at block 1, line 107
at block 1, line 91, in plot_county_7DAvg(df, title, size)
at /opt/python/envs/default/lib/python3.8/site-packages/seaborn/_decorators.pyline 46, in inner_f(*args, **kwargs)
at /opt/python/envs/default/lib/python3.8/site-packages/seaborn/relational.pyline 692, in lineplot(x, y, hue, size, style, data, palette, hue_order, hue_norm, sizes, size_order, size_norm, dashes, markers, style_order, units, estimator, ci, n_boot, seed, sort, err_style, err_kws, legend, ax, **kwargs)
at /opt/python/envs/default/lib/python3.8/site-packages/seaborn/relational.pyline 367, in __init__(self, data, variables, estimator, ci, n_boot, seed, sort, err_style, err_kws, legend)
at /opt/python/envs/default/lib/python3.8/site-packages/seaborn/_core.pyline 605, in __init__(self, data, variables)
at /opt/python/envs/default/lib/python3.8/site-packages/seaborn/_core.pyline 668, in assign_variables(self, data, variables)
at /opt/python/envs/default/lib/python3.8/site-packages/seaborn/_core.pyline 903, in _assign_variables_longform(self, data, **kwargs)
ValueError: Could not interpret value `DataDate` for parameter `x`# !/usr/bin/env python
author = "Michael Brown"
license = "Based off of sript by Sreenivas Bhattiprolu of Python for Microscopists"
import pandas as pd
import datetime as dt
from matplotlib import pyplot as plt
from datetime import timedelta
from warnings import simplefilter
simplefilter(action="ignore", category=pd.errors.PerformanceWarning)
# ===================================================================
# Example of Calcuation for Case Rate
# ===================================================================
# CVD['Daily100k'] = (CVD['DailyCases'] / statePopulation) * 100000
# CVD['100k7D'] = CVD['Daily100k'].rolling(window=7).mean()
CVD = pd.read_csv('https://opendata.maryland.gov/api/views/mgd3-qk8t/rows.csv?accessType=DOWNLOAD')
#Creating new data frame
AACounty = pd.DataFrame()
AACounty['ReportDate'] = CVD['ReportDate']
AACounty['DataDate'] = CVD['ReportDate']
#converting Report Date to string
AACounty['ReportDate'] = AACounty['ReportDate'].astype('str')
AACounty['DataDate'] = AACounty['DataDate'].astype('str')
#getting the date portion of the string
AACounty['ReportDate'] = AACounty.ReportDate.str.slice(0,10)
AACounty['DataDate'] = AACounty.DataDate.str.slice(0,10)
#converting string to date format
AACounty['ReportDate'] = [dt.datetime.strptime(x, '%m/%d/%Y')
for x in AACounty['ReportDate']]
AACounty['DataDate'] = [dt.datetime.strptime(x, '%m/%d/%Y')
for x in AACounty['DataDate']]
#adding new column for data date vs reported date - data date is 1 day prior to report date
AACounty['DataDate'] = AACounty['DataDate'] - timedelta(days=1)
AnneArundelPopulationDecennial2020 =588261
AnneArundelPOpulationACS2020 = 575421
AnneArundelPopulationACS2019 = 571275
AnneArundelPopulationPEP2019 = 579234
AnneArundelPopulationCounty = 579630
#Anne Arundel
AACounty['AnneArundel'] = CVD['ANNE']
AACounty['AADailyCases'] = AACounty['AnneArundel'].diff()
AACounty['AA7Day'] = AACounty['AADailyCases'].rolling(window=7).mean()
AACounty['AADaily100k2020Census'] = (AACounty['AADailyCases'] / AnneArundelPopulationDecennial2020) * 100000
AACounty['AA100k7D-2020Census'] = AACounty['AADaily100k2020Census'].rolling(window=7).mean()
AACounty['AACounty100k2020ACS'] = (AACounty['AADailyCases'] / AnneArundelPOpulationACS2020) * 100000
AACounty['AA100k7D-2020ACS'] = AACounty['AACounty100k2020ACS'].rolling(window=7).mean()
AACounty['AADaily100k2019ACS'] = (AACounty['AADailyCases'] / AnneArundelPopulationACS2019) * 100000
AACounty['AA100k7D-2019ACS'] = AACounty['AADaily100k2019ACS'].rolling(window=7).mean()
AACounty['AADaily100k2019PEP'] = (AACounty['AADailyCases'] / AnneArundelPopulationPEP2019) * 100000
AACounty['AA100k7D-2019PEP'] = AACounty['AADaily100k2019PEP'].rolling(window=7).mean()
AACounty['AADaily100kCounty'] = (AACounty['AADailyCases'] / AnneArundelPopulationCounty) * 100000
AACounty['AA100k7D-County'] = AACounty['AADaily100kCounty'].rolling(window=7).mean()
# Saving Data to CSV
print(AACounty.dtypes)
AACounty.to_csv('AnneArundel.csv')
#=================================================================================
# 7-Day Running Average - Daily Cases
#=================================================================================
def plot_county_7DAvg(df, title='7-Day Case Count', size=1):
#=================================================================================
# 7-Day Running Average - Daily Cases - All Counties
#=================================================================================
f, ax = plt.subplots(1, 1, figsize=(4 * size, 2 * size))
g = sns.lineplot(x="DataDate", y="AA7Day", data=df, color='red', label="Anne Arundel")
plt.legend(loc='upper left')
plt.xlabel('Date')
plt.ylabel(' 7-Day Average ')
plt.xticks(rotation=90)
plt.title(f' {title} ')
ax.grid(color='black', linestyle='dotted', linewidth=0.75)
plt.savefig(f'{title}.png')
plt.show()
cvd_case_rate_aggregate = AACounty.groupby(['ReportDate']).sum().reset_index()
sevenDayAverage60day = cvd_case_rate_aggregate.iloc[-60:]
sevenDayAverage30day = cvd_case_rate_aggregate.iloc[-30:]
sevenDayAverage7day = cvd_case_rate_aggregate.iloc[-7:]
plot_county_7DAvg(cvd_case_rate_aggregate, 'County Aggregate 7-Day Running Average', size=4)
plot_county_7DAvg(sevenDayAverage60day, 'County Past 60 Days 7-Day Running Average', size=4)
plot_county_7DAvg(sevenDayAverage30day, 'County Past 30 Days 7-Day Running Average', size=4)
plot_county_7DAvg(sevenDayAverage7day, 'County Past 7 Days 7-Day Running Average', size=4)
def plot_aacounty_7D100kAvg(df, title='Aggregate Anne Arundel County Case Rate', size=1):
#=================================================================================
# 7-Day Running Average - Case Rate - Anne Arundel County
#=================================================================================
f, ax = plt.subplots(1, 1, figsize=(5 * size, 3 * size))
g = sns.lineplot(x="ReportDate", y="AA100k7D-2020Census", data=df, color='black', linewidth=3.0, label="Anne Arundel Decennial 2020")
g = sns.lineplot(x="ReportDate", y="AA100k7D-2020ACS", data=df, color = 'darkgreen', linewidth=2.0, label="Anne Arundel ACS 2020")
g = sns.lineplot(x="ReportDate", y="AA100k7D-2019PEP", data=df, color='darkblue', linewidth=3.0, label="Anne Arundel PEP 2019 Estimate")
g = sns.lineplot(x="ReportDate", y="AA100k7D-2019ACS", data=df, color='darkmagenta', linewidth=2.0, label="Anne Arundel ACS 2019 Estimate")
g = sns.lineplot(x="ReportDate", y="AA100k7D-County", data=df, color='red', linewidth=2.0, label="Anne Arundel Estimate")
#g = sns.lineplot(x="ReportDate", y="AA100k7D", data=df, color='green', label="Anne Arundel")
plt.rcParams["figure.figsize"] = (200,100)
plt.xlabel('Date')
plt.ylabel('Cases per 100k')
plt.xticks(rotation=90)
plt.title(f' {title} ')
ax.grid(color='black', linestyle='dotted', linewidth=0.75)
plt.savefig(f'{title}.png')
plt.show()
aasevenday100kcvd_case_rate_aggregate = AACounty.groupby(['ReportDate']).sum().reset_index()
aasevenday100ksevenDayAverage60day = aasevenday100kcvd_case_rate_aggregate.iloc[-60:]
aasevenday100ksevenDayAverage30day = aasevenday100kcvd_case_rate_aggregate.iloc[-30:]
aasevenday100ksevenDayAverage7day = aasevenday100kcvd_case_rate_aggregate.iloc[-7:]
plot_aacounty_7D100kAvg(aasevenday100kcvd_case_rate_aggregate, 'County Case Rate Aggregate 7-Day Running Average', size=4)
plot_aacounty_7D100kAvg(aasevenday100ksevenDayAverage60day, 'County Case Rate Past 60 Days 7-Day Running Average', size=4)
plot_aacounty_7D100kAvg(aasevenday100ksevenDayAverage30day, 'County Case Rate Past 30 Days 7-Day Running Average', size=4)
plot_aacounty_7D100kAvg(aasevenday100ksevenDayAverage7day, 'County Case Rate Past 7 Days 7-Day Running Average', size=4)