We Keep Coding

iterate several polygons - 'Polygon object error'

I am constructing a graph to represent sales by country.
# to download the file
[file](https://drive.google.com/file/d/16Uw_rJgzJdqhhxYjK3tJGkTeXyOLENMR/view?usp=share_link)
store_sales = pd.read_pickle('store_sales.venta')
store_sales
p1_sales_by_country = store_sales.groupby(['country']).p1_sales.sum()
p1_sales_by_country
use a graph to represent sales values by country.
plt.figure(figsize=(16,6))
ax = plt.axes(projection=crs.PlateCarree())
shpfile = shapereader.natural_earth(resolution='110m',
category='cultural',
name='admin_0_countries')
reader = shapereader.Reader(shpfile)
countries = reader.records()
max_sales = p1_sales_by_country.max()
for country in countries:
country_name = country.attributes['ADM0_A3']
if country_name in p1_sales_by_country:
ax.add_geometries(country.geometry, crs.PlateCarree(),
facecolor=plt.cm.Greens(p1_sales_by_country[country_name]
/max_sales),
edgecolor='k')
else:
ax.add_geometries(country.geometry, crs.PlateCarree(),
facecolor='w',
edgecolor='k')
I have problems with iterating a Polygon
TypeError: 'Polygon' object is not iterable

Embedding python Matplotlib Graph in html using Pyscript

I've written a python program that takes some inputs and turns them into a matplotlib graph. Specifically, it displays wealth distributions by percentile for a country of the user's choosing. However, these inputs are currently given by changing variables in the program.
I want to put this code on a website, allowing users to choose any country and see the wealth distribution for that country, as well as how they compare. Essentially, I am trying to recreate this: https://wid.world/income-comparator/
The code in python is all done but I am struggling to incorporate it into an HTML file. I was trying to use pyscript but it currently loads forever and displays nothing. Would rather not rewrite it in javascript (mainly because I don't know js). My thoughts are that it has something to do with the code importing csv files from my device?
import csv
from typing import List
import matplotlib.pyplot as plt
import collections
import math
from forex_python.converter import CurrencyRates
# ---------------- #
# whether or not the graph includes the top 1 percent in the graph (makes the rest of the graph visible!)
one_percent = False # True or False
# pick which country(ies) you want to view
country = 'China' # String
# what currency should the graph use
currency_used = 'Canada' # String
# if you want to compare an income
compare_income = True # True or False
# what income do you want to compare
income = 100000 # Int
# ---------------- #
codes = {}
# get dictionary of monetary country codes
monetary_codes = {}
with open('codes-all.csv') as csv_file:
list = csv.reader(csv_file, delimiter=',')
for row in list:
if row[5] == "":
monetary_codes[row[0]] = (row[2], row[1])
# get dictionary of country names and codes for WID
with open('WID_countries.csv') as csv_file:
WID_codes = csv.reader(csv_file, delimiter=',')
next(WID_codes)
for row in WID_codes:
if len(row[0]) == 2:
if row[2] != "":
monetary_code = monetary_codes[row[1].upper()][0]
currency_name = monetary_codes[row[1].upper()][1]
codes[row[1].upper()] = (row[0], monetary_code, currency_name)
elif row[2] == "":
codes[row[1].upper()] = (row[0], 'USD', 'United States Dollar')
elif row[0][0] == 'U' and row[0][1] == 'S':
codes[row[1].upper()] = (row[0], 'USD', 'United States Dollar')
# converts user input to upper case
country = country.upper()
currency_used = currency_used.upper()
# gets conversion rate
c = CurrencyRates()
conversion_rate = c.get_rate(codes[country][1], codes[currency_used][1])
# convert money into correct currency
def convert_money(conversion_rate, value):
return float(value) * conversion_rate
# get and clean data
def get_data(country):
aptinc = {}
# cleaning the data
with open(f'country_data/WID_data_{codes[country][0]}.csv') as csv_file:
data = csv.reader(csv_file, delimiter=';')
for row in data:
# I only care about the year 2021 and the variable 'aptinc'
if 'aptinc992' in row[1] and row[3] == '2021':
# translates percentile string into a numerical value
index = 0
for i in row[2]:
# index 0 is always 'p', so we get rid of that
if index == 0:
row[2] = row[2][1:]
# each string has a p in the middle of the numbers we care about. I also only
# care about the rows which measure a single percentile
# (upper bound - lower bound <= 1)
elif i == 'p':
lb = float(row[2][:index - 1])
ub = float(row[2][index:])
# if the top one percent is being filtered out adds another requirement
if not one_percent:
if ub - lb <= 1 and ub <= 99:
row[2] = ub
else:
row[2] = 0
else:
if ub - lb <= 1:
row[2] = ub
else: row[2] = 0
index += 1
# adds wanted, cleaned data to a dictionary. Also converts all values to one currency
if row[2] != 0:
aptinc[row[2]] = convert_money(conversion_rate, row[4])
return aptinc
# find the closest percentile to an income
def closest_percentile(income, data):
closest = math.inf
percentile = float()
for i in data:
difference = income - data[i]
if abs(difference) < closest:
closest = difference
percentile = i
return percentile
# ---------------- #
unsorted_data = {}
percentiles = []
average_income = []
# gets data for the country
data = get_data(country)
for i in data:
unsorted_data[i] = data[i]
# sorts the data
sorted = collections.OrderedDict(sorted(unsorted_data.items()))
for i in sorted:
percentiles.append(i)
average_income.append(data[i])
# makes countries pretty for printing
country = country.lower()
country = country.capitalize()
# calculates where the income places against incomes from country(ies)
blurb = ""
if compare_income:
percentile = closest_percentile(income, sorted)
blurb = f"You are richer than {round(percentile)} percent of {country}'s population"
# plot this data!
plt.plot(percentiles,average_income)
plt.title(f'{country} Average Annual Income by Percentile')
plt.xlabel(f'Percentile\n{blurb}')
plt.ylabel(f'Average Annual Income of {country}({codes[currency_used][1]})')
plt.axvline(x = 99, color = 'r', label = '99th percentile', linestyle=':')
if compare_income:
plt.axvline(x = percentile, color = 'g', label = f'{income} {codes[currency_used][2]}')
plt.legend(bbox_to_anchor = (0, 1), loc = 'upper left')
plt.show()

Why are the indicators on my chart delayed by at least 1 day, making them not flush on the blue line? Is it because the time frame is too wide?

Why are the up triangles, when the program is supposed to buy, not on the line when it crosses under, or in the other scenario, the down triangle, when the program is supposed to sell, not on the line when it crosses on top? The blue line is the price and the red line is the EMA, tracking the price.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import requests
plt.style.use("fivethirtyeight")
df = pd.read_csv("TSLA.csv")
df = df.set_index(pd.DatetimeIndex(df["Date"].values))
ShortEMA = df.Close.ewm(span=5, adjust = False).mean()
MiddleEMA = df.Close.ewm(span = 21, adjust = False).mean()
LongEMA = df.Close.ewm(span = 53, adjust = False).mean()
df['Short'] = ShortEMA
df['Middle'] = MiddleEMA
df['Long'] = LongEMA
def MyStrat(data):
bought_list = []
sold_list = []
In = False
Out = True
for i in range(0, len(data)):
if data["Close"][i] > data["Short"][i] and In == False and Out == True:
bought_list.append(data["Close"][i])
sold_list.append(np.nan)
In = True
Out = False
elif data["Close"][i] < data["Short"][i] and In == True and Out == False:
sold_list.append(data["Close"][i])
bought_list.append(np.nan)
In = False
Out = True
else:
bought_list.append(np.nan)
sold_list.append(np.nan)
return(bought_list,sold_list)
df["Bought"] = MyStrat(df)[0]
df["Sold"] = MyStrat(df)[1]
print(df)
plt.figure(figsize=(16, 5))
plt.title('Buy and Sell', fontsize = 18)
plt.plot(df['Close'], label = 'Close Price', color = 'blue', alpha = 0.35)
plt.plot(ShortEMA, label = 'Short', color = 'red', alpha = 0.35)
plt.scatter(df.index, df["Bought"], color = "purple", marker = "^", alpha = 1)
plt.scatter(df.index, df["Sold"], color = "blue", marker = "v", alpha = 1)
plt.xlabel("Date", fontsize = 18)
plt.ylabel("Close", fontsize = 18)
plt.show()
You can use this data for reference:
Date,Open,High,Low,Close,Adj Close,Volume
2022-01-06,1077.000000,1088.000000,1020.500000,1064.699951,1064.699951,30112200
2022-01-07,1080.369995,1080.930054,1010.000000,1026.959961,1026.959961,28054900
2022-01-10,1000.000000,1059.099976,980.000000,1058.119995,1058.119995,30605000
2022-01-11,1053.670044,1075.849976,1038.819946,1064.400024,1064.400024,22021100
2022-01-12,1078.849976,1114.839966,1072.589966,1106.219971,1106.219971,27913000
2022-01-13,1109.069946,1115.599976,1026.540039,1031.560059,1031.560059,32403300
2022-01-14,1019.880005,1052.000000,1013.380005,1049.609985,1049.609985,24308100
2022-01-18,1026.609985,1070.790039,1016.059998,1030.510010,1030.510010,22247800
2022-01-19,1041.709961,1054.670044,995.000000,995.650024,995.650024,25147500
2022-01-20,1009.729980,1041.660034,994.000000,996.270020,996.270020,23496200
2022-01-21,996.340027,1004.549988,940.500000,943.900024,943.900024,34472000
2022-01-24,904.760010,933.510010,851.469971,930.000000,930.000000,50521900
2022-01-25,914.200012,951.260010,903.210022,918.400024,918.400024,28865300
2022-01-26,952.429993,987.690002,906.000000,937.409973,937.409973,34955800
2022-01-27,933.359985,935.390015,829.000000,829.099976,829.099976,49036500
2022-01-28,831.559998,857.500000,792.010010,846.349976,846.349976,44929700
2022-01-31,872.710022,937.989990,862.049988,936.719971,936.719971,34812000
2022-02-01,935.210022,943.700012,905.000000,931.250000,931.250000,24379400
2022-02-02,928.179993,931.500000,889.409973,905.659973,905.659973,22264300
2022-02-03,882.000000,937.000000,880.520020,891.140015,891.140015,26285200
2022-02-04,897.219971,936.500000,881.169983,923.320007,923.320007,24541800
2022-02-07,923.789978,947.770020,902.710022,907.340027,907.340027,20331500
2022-02-08,905.530029,926.289978,894.799988,922.000000,922.000000,16909700
2022-02-09,935.000000,946.270020,920.000000,932.000000,932.000000,17419800
2022-02-10,908.369995,943.809998,896.700012,904.549988,904.549988,22042300
2022-02-11,909.630005,915.960022,850.700012,860.000000,860.000000,26548600
2022-02-14,861.570007,898.880005,853.150024,875.760010,875.760010,22585500
2022-02-15,900.000000,923.000000,893.380005,922.429993,922.429993,19095400
2022-02-16,914.049988,926.429993,901.210022,923.390015,923.390015,17098100
2022-02-17,913.260010,918.500000,874.099976,876.349976,876.349976,18392800
2022-02-18,886.000000,886.869995,837.609985,856.979980,856.979980,22833900
2022-02-22,834.130005,856.729980,801.099976,821.530029,821.530029,27762700
2022-02-23,830.429993,835.299988,760.559998,764.039978,764.039978,31752300
2022-02-24,700.390015,802.479980,700.000000,800.770020,800.770020,45107400
2022-02-25,809.229980,819.500000,782.400024,809.869995,809.869995,25355900
2022-02-28,815.010010,876.859985,814.710022,870.429993,870.429993,33002300
2022-03-01,869.679993,889.880005,853.780029,864.369995,864.369995,24922300
2022-03-02,872.130005,886.479980,844.270020,879.890015,879.890015,24881100
2022-03-03,878.770020,886.440002,832.599976,839.289978,839.289978,20541200
2022-03-04,849.099976,855.650024,825.159973,838.289978,838.289978,22333200
2022-03-07,856.299988,866.140015,804.570007,804.580017,804.580017,24164700
2022-03-08,795.530029,849.989990,782.169983,824.400024,824.400024,26799700
2022-03-09,839.479980,860.559998,832.010010,858.969971,858.969971,19728000
2022-03-10,851.450012,854.450012,810.359985,838.299988,838.299988,19549500
2022-03-11,840.200012,843.799988,793.770020,795.349976,795.349976,22272800
2022-03-14,780.609985,800.700012,756.039978,766.369995,766.369995,23717400
2022-03-15,775.270020,805.570007,756.570007,801.890015,801.890015,22280400
2022-03-16,809.000000,842.000000,802.260010,840.229980,840.229980,28009600
2022-03-17,830.989990,875.000000,825.719971,871.599976,871.599976,22194300
2022-03-18,874.489990,907.849976,867.390015,905.390015,905.390015,33408500
2022-03-21,914.979980,942.849976,907.090027,921.159973,921.159973,27327200
2022-03-22,930.000000,997.859985,921.750000,993.979980,993.979980,35289500
2022-03-23,979.940002,1040.699951,976.400024,999.109985,999.109985,40225400
2022-03-24,1009.729980,1024.489990,988.799988,1013.919983,1013.919983,22973600
2022-03-25,1008.000000,1021.799988,997.320007,1010.640015,1010.640015,20642900
2022-03-28,1065.099976,1097.880005,1053.599976,1091.839966,1091.839966,34168700
2022-03-29,1107.989990,1114.770020,1073.109985,1099.569946,1099.569946,24538300
2022-03-30,1091.170044,1113.949951,1084.000000,1093.989990,1093.989990,19955000
2022-03-31,1094.569946,1103.140015,1076.640015,1077.599976,1077.599976,16265600
2022-03-31,1094.569946,1103.139893,1076.640991,1077.599976,1077.599976,16330919

The problem with this is that the point of intersection occurs between days, not on a specific day. As the data is not continuous, but rather just one point per business day, it is not possible to put the arrow on the intersection itself. I have enlarged a portion of the graph here so you can see what I mean. The change occurs between the 9th and 10th. The data is only on the 9th or the 10th, so the arrow is plotted, and the buy occurs, on the 10th.
The buy/sell is on the next possible day, causing the mis-alignment of the arrows.

Slight challenge. Need to optimize code. Original one takes too long :(

So i'm trying to read 3 different csv files and plotting the information in an img with four graphs.
One with the average delay by airline, expressed in minutes
Another with the ratio of delayed flights, by airline
Another with the average delay by destination airport, expressed in minutes
And finally another with the ratio of flights delayed to arrival, by destination airport
All the information is correct and i got it from the files. The problem is that the program below takes too long to produce the graphs and that they're all being separately plotted and not all together in one image. Is there a way to optimize my code to run faster? And how do i use subplots without changing everything?
import pandas as pd
import matplotlib.pyplot as plt
path_main = '850566403_T_ONTIME.csv'
path_airline = 'L_AIRLINE_ID.csv'
path_airport = 'L_AIRPORT_ID.csv'
df1 = pd.read_csv(path_main)
al = pd.read_csv(path_airline)
ap = pd.read_csv(path_airport)
#remove columns and rows with nan
df1.dropna(axis=1, how='all', inplace=True)
df = df1.dropna(subset=['ARR_DELAY_NEW'])
#------------------------------------------------------------------------------
#Airlines:
#dict with {ID: Name}
d_al = {}
for i in range(len(al)):
d_al[al['Code'][i]] = al['Description'][i]
# array with ID's of airlines and delays
arr_al = df.loc[:, ('AIRLINE_ID', 'ARR_DELAY_NEW')].to_numpy()
# list with ID's of airlines
list_al = []
for i in arr_al:
if i[0] not in list_al:
list_al.append(int(i[0]))
def airline_avg_ratio(ID):
'''
function that requires an airline ID
and returns a tuple with name (first 10
characters), average delay and
delayed flight ratios
'''
nr_voos = 0
soma = 0
nr_atrasos = 0
for i in arr_al:
if i[0] == ID:
soma += i[1]
nr_voos += 1
if i[1] != 0:
nr_atrasos += 1
for k,v in d_al.items():
if k == ID:
nome = v[0:10]
media = round((soma / nr_atrasos), 3)
racio = round((nr_atrasos / nr_voos), 3)
return (nome, media, racio)
dados_al = []
for i in list_al:
dados_al.append(airline_avg_ratio(i))
df_al = pd.DataFrame(dados_al, columns=['Airlines', 'Average', 'Ratio'])
graph1 = df_al.drop(columns='Ratio').sort_values(by='Average').iloc[-10:]
graph1.plot(x='Airlines', y='Average', kind='bar')
plt.title("Atraso Médio por Companhia (top 10)")
plt.xlabel('Companhia Aérea', fontsize=12)
plt.ylabel('Minutos', fontsize=12)
plt.show()
graph2 = df_al.drop(columns='Average').sort_values(by='Ratio').iloc[-10:]
graph2.plot(x='Airlines', y='Ratio', kind='bar')
plt.title("Vôos Atrasados por Companhia (top 10)")
plt.xlabel('Companhia Aérea', fontsize=12)
plt.ylabel('Rácio', fontsize=12)
plt.show()
#------------------------------------------------------------------------------
# Airports:
#dict with {ID: Name}
d_ap = {}
for i in range(len(ap)):
d_ap[ap['Code'][i]] = ap['Description'][i]
#array with ID's of Airports and delays
arr_ap = df.loc[:, ('DEST_AIRPORT_ID', 'ARR_DELAY_NEW')].to_numpy()
#list with ID's of Airports
list_ap = []
for i in arr_ap:
if i[0] not in list_ap:
list_ap.append(int(i[0]))
def airport_avg_ratio(ID):
'''
function that requires an airport
and returns a tuple with name (first 10
characters), average delay and
delayed flight ratios
'''
nr_chegadas = 0
soma = 0
nr_atrasos = 0
for i in arr_ap:
if i[0] == ID:
soma += i[1]
nr_chegadas += 1
if i[1] != 0:
nr_atrasos += 1
for k,v in d_ap.items():
if k == ID:
nome = v[0:10]
media = round((soma / nr_atrasos), 3)
racio = round((nr_atrasos / nr_chegadas), 3)
return (nome, media, racio)
dados_ap = []
for i in list_ap:
dados_ap.append(airport_avg_ratio(i))
df_ap = pd.DataFrame(dados_ap, columns=['Airports', 'Average', 'Ratio'])
graph3 = df_ap.drop(columns='Ratio').sort_values(by='Average').iloc[-10:]
graph3.plot(x='Airports', y='Average', kind='bar')
plt.title("Atraso Médio por Aeroporto (top 10)")
plt.xlabel('Aeroporto', fontsize=12)
plt.ylabel('Minutos', fontsize=12)
plt.show()
graph4 = df_ap.drop(columns='Average').sort_values(by='Ratio').iloc[-10:]
graph4.plot(x='Airports', y='Ratio', kind='bar')
plt.title("Vôos Atrasados por Aeroporto (top 10)")
plt.xlabel('Aeroporto', fontsize=12)
plt.ylabel('Rácio', fontsize=12)
plt.show()

Adding a Title or Text to a Folium Map

I'm wondering if there's a way to add a title or text on a folium map in python?
I have 8 maps to show and I want the user to know which map they're looking at without having to click on a marker. I attempted to add an image of the map, but couldn't because I don't have high enough reputation score.
My code:
#marker cluster
corpus_chris_loc = [27.783889, -97.510556]
harvey_avg_losses_map = folium.Map(location = corpus_chris_loc, zoom_start = 5)
marker_cluster = MarkerCluster().add_to(harvey_avg_losses_map)
#inside the loop add each marker to the cluster
for row_index, row_values in harvey_losses.iterrows():
loc = [row_values['lat'], row_values['lng']]
pop = ("zip code: " + str(row_values["loss_location_zip"]) + "\nzip_avg: " + "$" + str(row_values['zip_avg'])) #show the zip and it's avg
icon = folium.Icon(color='red')
marker = folium.Marker(
title = "Harvey: " + "$" + str(row_values['harvey_avg']),
location = loc,
popup = pop,
icon=icon)
marker.add_to(marker_cluster)
#save an interactive HTML map by calling .save()
harvey_avg_losses_map.save('../data/harveylossclustermap.html')
harvey_avg_losses_map[map of hurricane harvey insurance claims][1]

Of course you can add a title to a Folium map.
For example:
import folium
loc = 'Corpus Christi'
title_html = '''
<h3 align="center" style="font-size:16px"><b>{}</b></h3>
'''.format(loc)
m = folium.Map(location=[27.783889, -97.510556],
zoom_start=12)
m.get_root().html.add_child(folium.Element(title_html))
m.save('map-with-title.html')
m