date_options[weeks] = date_item.strftime("%b %d")
else:
date_options[weeks] = date_item.strftime("%b %d")
weeks = weeks + 1
#Pick a default date
inprogress = data_US['date'][data_US.index[-3]]
first_date = data_US['date'][data_US.index[0]]
last_date = data_US['date'][data_US.index[-1]]
#Set up the charts
import plotly.express as px
import plotly.graph_objects as go
#fig = go.Figure() # or any Plotly Express function e.g. px.bar(...)
fig = px.choropleth()
bar1 = px.bar()
bar2 = px.bar()
colorscale = [
"#f7fbff", "#ebf3fb", "#deebf7", "#d2e3f3", "#c6dbef", "#b3d2e9",
"#9ecae1", "#85bcdb", "#6baed6", "#57a0ce", "#4292c6", "#3082be",
"#2171b5", "#1361a9", "#08519c", "#0b4083", "#08306b"
] # or px.colors.sequential.Plasma
#Style the charts
plotcfg = {'displayModeBar': False}
#fig1.update_xaxes(rangeslider_visible=True)
fig.update_layout(height=500,
margin=dict(l=0, r=0, b=0, t=0, pad=0),
coloraxis_colorbar=dict(title="Z-score"),
fig = px.line(y=data,
x=year,
template='plotly_dark',
title=country_name + ' Population in largest city',
labels=dict(x="Years", y="Population in largest city"))
fig.show()
a = input('Your Country Name: __ ')
try:
specific_country(a)
except:
print('Invalid Country Name')
df = df.sort_values(by='2019', ascending=False)
df = pd.melt(df, id_vars=['Country Name', 'Country Code'], value_vars=lista)
print(df)
fig = px.choropleth(
df, # Input Dataframe
locations="Country Code", # identify country code column
color="value", # identify representing column
hover_name="Country Name", # identify hover name
animation_frame="variable", # identify date column
projection="natural earth", # select projection
color_continuous_scale='Peach', # select prefer color scale
range_color=[-6, 6] # select range of dataset
)
fig.show()
# In[ ]:
dates = date_cols*len(covid_conf['Country/Region'])
values = np.array([list(i) for i in covid_conf[date_cols].iloc]).flatten()
data = pd.DataFrame({'country':countries, 'date':dates, 'confirmed':values})
data
# In[ ]:
fig = px.choropleth(data, locations='country', color='confirmed', animation_frame='date')
fig.show()
# In[ ]:
# In[ ]:
#aggregate based on states
agg_state = (extra_data.drop(['Metro_meta','Year','Month','Labor_Force',
'Employment',
'Unemployment','date', 'Metro'], axis=1))
agg_state=agg_state.groupby('States').mean()
# In[ ]:
type(list(agg_state.index))
import plotly.express as px
import plotly.graph_objects as go
import matplotlib.pyplot as plt
fig = go.Figure(px.choropleth(locations=agg_state.index, locationmode="USA-states", color= agg_state.values, scope="usa"))
fig.update_layout(title="Average Unemployment Rate by State")
fig.data[-1].showlegend = True
fig.update_layout(legend_title='<b> Unemployment Rate </b>')
fig.show()
# In[ ]:
#plot avg unemployment by county
#first figure out how to ID county -- use FIPS code -- this is in the metro metadata
#isolate the fips codes
#get state level information
fips = []
#from the metro meta data, isolate just the fips
for i in range(4,142564):
fips.append(str((extra_data['Metro_meta'][i][2:7]).strip()))
data.info() # In[7]: data.describe() # ## Visualiize the data with plotly # In[8]: fig = px.choropleth(data,locations='Country',locationmode='country names',color='Confirmed',animation_frame='Date') fig.update_layout(title='Choropleth Map of Confirmed Cases -till today',template="plotly_dark") fig.show() # In[9]: fig = px.choropleth(data,locations='Country',locationmode='country names',color='Confirmed',animation_frame='Date',scope='africa') fig.update_layout(title='Choropleth Map of Confirmed Cases - Africa till today',template="plotly_dark") fig.show() # ## Spread over Time # In[10]:
- Statistics for Data Scientists: Sat, 10:30-12:00
- How to Win TAMU Datathon: Sat, 13:00-14:00
- Data Wrangling: Sat, 17:00-18:15
- Data Visualization: Sat, 18:30-19:45
- Machine Learning Part 1 - Theory: Sat, 20:00-21:15
- Machine Learning Part 2 - Applied: Sat, 21:30-22:45
""")
df = pd.read_csv(
'https://drive.google.com/uc?id=1hSMhl-JeTCX-t72KjhasTQoL1LdWSRhw')
st.write(df.head())
df_1 = px.data.gapminder()
fig = px.choropleth(df_1,
locations="iso_alpha",
color="lifeExp",
hover_name="country",
animation_frame="year",
range_color=[20, 80])
st.write(fig)
movehub_rating = "None" #@param ["None", "Low", "Med", "High"]
purchase_power = "High" #@param ["None", "Low", "Med", "High"]
health_care = "Low" #@param ["None", "Low", "Med", "High"]
quality_of_life = "None" #@param ["None", "Low", "Med", "High"]
pollution = "None" #@param ["None", "Low", "Med", "High"]
crime_rating = "None" #@param ["None", "Low", "Med", "High"]
weights = [
movehub_rating,
purchase_power,
health_care,
plot_values = {"Positive tests":"positive",
"Total tests":"totalTestResults",
"Percent increase (rolling day-to-day)":"perc_increase",
"Percent increase (five-day rolling average)":"perc_five_increase",
"Percent deaths":"perc_death",
"Percent hospitalized":"perc_hosp"}
mostrecent = sorted(data["date"],reverse=True)[0]
tmp = data.loc[data["date"] == mostrecent][["state","positive"]].dropna()
tmp["state"].values
state_map_fig = px.choropleth(locations=tmp["state"].values,
locationmode="USA-states",
color=np.log10(tmp["positive"].replace(0,1)).values,
scope="usa")
app.layout = html.Div([
html.H1('COVID-19 statistics from covidtracking.com'),
dcc.Tabs(id="plot-tabs",
value='state-positive',
children = [
dcc.Tab(label='State Stats over Time', value='state-positive'),
dcc.Tab(label='US State Heatmap', value='us-state-map'),
]),
html.Div(id='plot-tabs-contents') # generate from render content function below, as callback.
])
@app.callback(Output('plot-tabs-contents', 'children'),
def update_graph(cat_selected, date_selected):
print(cat_selected)
print(date_selected)
date = YEARS.get(date_selected)
only_one_day = our_df[our_df['date'] == date]
if cat_selected == 'ActPerPop':
fig = px.choropleth(
only_one_day,
locations="isocode",
color="ActPerPop", # This will determine the color
hover_name="country", # column to add to hover information
# template = 'plotly_dark' ,
width=1300,
height=500,
color_continuous_scale=px.colors.sequential.YlOrRd)
if cat_selected == 'CnfPerPop':
fig = px.choropleth(
only_one_day,
locations="isocode",
color="CnfPerPop", # This will determine the color
hover_name="country", # column to add to hover information
# template = 'plotly_dark' ,
width=1300,
height=500,
color_continuous_scale=px.colors.sequential.YlOrRd)
if cat_selected == 'RecPerCnf':
fig = px.choropleth(
only_one_day,
locations="isocode",
color="RecPerCnf", # This will determine the color
hover_name="country", # column to add to hover information
# template = 'plotly_dark'
width=1300,
height=500,
color_continuous_scale=px.colors.sequential.YlOrRd)
if cat_selected == 'DecPerCnf':
fig = px.choropleth(
only_one_day,
locations="isocode",
color="DecPerCnf", # This will determine the color
hover_name="country", # column to add to hover information
# template = 'plotly_dark' ,
width=1300,
height=500,
color_continuous_scale=px.colors.sequential.YlOrRd)
fig.update_layout(
# title = str(date_selected) + " Worst hit countries" ,
title="Date Selected is : " + date,
# width = 1200,
autosize=True,
# margin = dict(l = 40 , r = 40 , t = 40 , b = 40) ,
paper_bgcolor="LightSteelBlue",
)
#
# if "layout" in figure :
# lat = figure["layout"]["mapbox"]["center"]["lat"]
# lon = figure["layout"]["mapbox"]["center"]["lon"]
# zoom = figure["layout"]["mapbox"]["zoom"]
# else :
lat = 38.72490
lon = -95.61446
zoom = 3.5
layout = dict(
mapbox=dict(
layers=[],
accesstoken=mapbox_access_token,
style=mapbox_style,
center=dict(lat=lat, lon=lon),
zoom=zoom,
),
hovermode="closest",
margin=dict(r=0, l=0, t=0, b=0),
# annotations = annotations ,
dragmode="lasso",
)
# fig = dict( layout = layout)
return fig
import pandas as pd
import plotly.express as px
# Source for basis of mapping Script: https://gist.github.com/jbrobst
df = pd.read_csv(r"C:\Users\Arnav Joshi\OxygenNeed.csv")
fig = px.choropleth(
df,
geojson=
"https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson",
featureidkey='properties.ST_NM',
locations='State',
color='Oxygen Needed Daily(tonnes)',
color_continuous_scale='Blues')
fig.update_geos(fitbounds="locations", visible=False)
fig.show()
import pandas as pd
import plotly.express as px
# load in the dataset
df = pd.read_csv("../data/share-of-individuals-using-the-internet.csv")
# extract data for 2016
df_2016 = df[df['Year'] == 2016]
print(df_2016.shape)
print(df.columns)
plot = px.choropleth(
data_frame=df_2016,
locations='Country',
color='Individuals using the Internet (% of population)',
locationmode='country names',
hover_name='Country',
title=
"Internet usage across countries of the world as a percentage of the total population in 2016."
)
plot.show()
import plotly.express as px
df = px.data.election()
geojson = px.data.election_geojson()
fig = px.choropleth(df,
geojson=geojson,
color="Bergeron",
locations="district",
featureidkey="properties.district",
projection="mercator")
fig.update_geos(fitbounds="locations", visible=False)
fig.update_layout(margin={"r": 0, "t": 0, "l": 0, "b": 0})
fig.show()
states_geojson = json.load(file)
geojson_state_code_map = {}
for feature in states_geojson["features"]:
feature['id'] = feature['properties']['state_code']
geojson_state_code_map[feature['properties']['st_nm'].upper(
)] = feature['properties']['state_code']
state_id_map = {}
with open('../library/overall_state_frequency.csv', 'r', newline='') as file:
for row in csv.DictReader(file):
state = row["State"]
if state == "DELHI":
state_id_map[state] = geojson_state_code_map["NCT OF DELHI"]
else:
state_id_map[state] = geojson_state_code_map[
difflib.get_close_matches(state,
geojson_state_code_map.keys())[0]]
df = pd.read_csv('../library/overall_state_frequency.csv')
df['Frequency'] = df['Frequency'].apply(lambda x: int(x))
df['id'] = df['State'].apply(lambda x: state_id_map.get(x, 0))
df['Frequency_Scale'] = np.log10(df['Frequency'])
fig = px.choropleth(df,
locations='id',
geojson=states_geojson,
color='Frequency',
scope='asia')
fig.update_geos(fitbounds="locations", visible=False)
fig.write_image("../images/overall_state_frequency.png")
def update_graph(option_slctd, data_slctd, scope_slctd, cumil_slctd):
print(option_slctd)
print(data_slctd)
print(scope_slctd)
print(cumil_slctd)
#cumil_slctd=False
dff1 = df1.copy()
dff1 = dff1[dff1["month_num"] == option_slctd]
container = "The data chosen by user is {0} and the geographical scope is {1}".format(
data_slctd, scope_slctd)
if (cumil_slctd == 'non_cumil'):
if data_slctd == "deaths":
fig = px.choropleth(
data_frame=dff1,
locationmode='ISO-3',
locations='iso_code',
scope=scope_slctd,
color="new_deaths",
hover_data=[
'location', 'new_deaths', 'hospital_beds_per_thousand'
],
color_continuous_scale=px.colors.diverging.Geyser)
elif data_slctd == "affected_cases":
fig = px.choropleth(
data_frame=dff1,
locationmode='ISO-3',
locations='iso_code',
scope=scope_slctd,
color="new_cases",
hover_data=[
'location', 'new_cases', 'hospital_beds_per_thousand'
],
color_continuous_scale=px.colors.diverging.Geyser)
else:
fig = px.choropleth(
data_frame=dff1,
locationmode='ISO-3',
locations='iso_code',
scope=scope_slctd,
color="new_tests",
hover_data=[
'location', 'new_tests', 'hospital_beds_per_thousand'
],
color_continuous_scale=px.colors.diverging.Geyser)
else:
if data_slctd == "deaths":
fig = px.choropleth(
data_frame=dff1,
locationmode='ISO-3',
locations='iso_code',
scope=scope_slctd,
color="cumil_deaths",
hover_data=[
'location', 'cumil_deaths', 'hospital_beds_per_thousand'
],
color_continuous_scale=px.colors.diverging.Geyser)
elif data_slctd == "affected_cases":
fig = px.choropleth(
data_frame=dff1,
locationmode='ISO-3',
locations='iso_code',
scope=scope_slctd,
color="cumil_cases",
hover_data=[
'location', 'cumil_cases', 'hospital_beds_per_thousand'
],
color_continuous_scale=px.colors.diverging.Geyser)
else:
fig = px.choropleth(
data_frame=dff1,
locationmode='ISO-3',
locations='iso_code',
scope=scope_slctd,
color="cumil_tests",
hover_data=[
'location', 'cumil_tests', 'hospital_beds_per_thousand'
],
color_continuous_scale=px.colors.diverging.Geyser)
#LineGraph
if data_slctd == "deaths":
img = px.line(dff3,
x=dff3['location'],
y=dff3['cumil_deaths'],
title='Line Graph for Total Deaths')
#img.show()
elif data_slctd == "affected_cases":
img = px.line(dff3,
x=dff3['location'],
y=dff3['cumil_cases'],
title='Line Graph for Total Affected Cases')
else:
img = px.line(dff3,
x=dff3['location'],
y=dff3['cumil_tests'],
title='Line Graph for Total Tests')
return container, fig, img
covid19_us_states['confirmed_cases_category'] = covid19_us_states['confirmed'].apply(lambda x: confirmed_case_category(x))
covid19_us_states.head()
covid19_us_states['confirmed_cases_category'] = pd.Categorical(covid19_us_states['confirmed_cases_category'], ordered=True,
categories=['< 1000', '> 1000', '> 10000','> 50000'])
covid19_us_states.dtypes
covid19_us_states.head()
covid19_us_states['confirmed_cases_category'].unique()
import plotly.express as px
import matplotlib.pyplot as plt
fig = px.choropleth(covid19_us_states, color='confirmed', color_continuous_scale="Rainbow",
locations='state', locationmode="USA-states",scope="usa")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()
import plotly.express as px
import matplotlib.pyplot as plt
fig = px.choropleth(covid19_us_states, color='deaths', color_continuous_scale="reds",
locations='state', locationmode="USA-states",scope="usa")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()
covid19_us_states = covid19_us_data.groupby(['state','province']).agg('sum')
covid19_us_states = covid19_us_states[['confirmed','deaths','recovered']]
covid19_us_states =covid19_us_states.reset_index()
# GroupingBy the dataset for the map
formated_gdf = covid_cases.groupby(['Date_x', 'Country'])[
'Confirmed', 'Deaths', 'Recovered'].max()
formated_gdf = formated_gdf.reset_index()
formated_gdf['Date'] = pd.to_datetime(formated_gdf['Date_x'])
formated_gdf['Date'] = formated_gdf['Date'].dt.strftime('%m/%d/%Y')
formated_gdf['log_ConfirmedCases'] = np.log(formated_gdf.Confirmed + 1)
formated_gdf['log_Deaths'] = np.log(formated_gdf.Deaths + 1)
# Plotting the figure
fig = px.choropleth(formated_gdf, locations="Country", locationmode='country names',
color="log_ConfirmedCases", hover_name="Country", projection="mercator",
animation_frame="Date", width=1000, height=800,
color_continuous_scale=px.colors.sequential.Viridis,
title='The Spread of COVID-19 Cases Across World')
# Showing the figure
fig.update(layout_coloraxis_showscale=True)
py.offline.iplot(fig)
if query == '3':
# reference from: https://www.kaggle.com/aestheteaman01/demographics-observation-for-pandemic-escalation
# #Which-populations-are-at-risk-of-contracting-COVID-19?
fig = px.choropleth(formated_gdf, locations="Country", locationmode='country names',
color="log_Deaths", hover_name="Country", projection="mercator",
animation_frame="Date", width=1000, height=800,
color_continuous_scale=px.colors.sequential.Viridis,
title='The COVID-19 Deaths Cases Across World')
just_ML = c[
(c['Q8'] ==
'We have well established ML methods (i.e., models in production for more than 2 years)'
)
|
(c['Q8'] ==
'We recently started using ML methods (i.e., models in production for less than 2 years)'
)
|
(c['Q8'] ==
'We use ML methods for generating insights (but do not put working models into production)'
)]
import plotly.express as px # Be sure to import express
fig = px.choropleth(
countries, # Input Pandas DataFrame
locations="country", # DataFrame column with locations
color="N° of answers", # DataFrame column with color values
locationmode='country names', # Set to plot
color_continuous_scale='viridis')
fig.update_layout(title_text='2019 Kaggle survey respondents per country')
fig.show() # Output the plot to the screen
fig = plt.figure(figsize=(15, 5))
ax1 = plt.subplot2grid((1, 2), (0, 0))
sns.countplot(c.Q1, order=c['Q1'].value_counts().index, palette='viridis')
plt.title('AGE', fontsize=15, weight='bold')
ax1 = plt.subplot2grid((1, 2), (0, 1))
sns.countplot(c.Q2, palette='viridis')
plt.title('GENDER', fontsize=15, weight='bold')
plt.show()
plt.figure(figsize=(15, 5))
county_data['Age_0_4'].sum(), county_data['Age_5_14'].sum(),
county_data['Age_15_24'].sum(), county_data['Age_25_34'].sum(),
county_data['Age_35_44'].sum(), county_data['Age_45_54'].sum(),
county_data['Age_55_64'].sum(), county_data['Age_65_74'].sum(),
county_data['Age_85plus'].sum()
])
plt.title('Covid Cases by Age')
st.pyplot()
fig = px.choropleth(county_data,
geojson=counties,
locations='COUNTY',
color='T_positive',
color_continuous_scale="Viridis",
hover_name='COUNTYNAME',
hover_data=[
'Age_0_4', 'Age_5_14', 'Age_25_34', 'Age_35_44',
'Age_45_54', 'Age_55_64', 'Age_65_74', 'Age_85plus'
],
scope="usa",
title="Positive Test Cases",
range_color=(0, 10000))
fig.update_geos(projection={'scale': 4},
center={
'lat': 27.6648,
'lon': -81.5158
},
visible=False)
st.plotly_chart(fig)
'''
From the data we can see that the largest age range that has tested positive for COVID-19 is 25
'% of guests'] = country_data['Number of Guests'] / total_guests * 100
country_data['country'] = country_data.index
country_data.drop(columns='country', inplace=True)
fig = px.pie(
country_data,
values='Number of Guests',
names=country_data.index,
title='Home Country of Guests by %',
template='seaborn',
)
fig.update_traces(textposition="inside", textinfo="value+percent+label")
guest_map = px.choropleth(country_data,
locations=country_data.index,
color=country_data['% of guests'],
hover_name=country_data.index,
color_continuous_scale='Viridis',
title="Home country of guests")
# fig.show()
# guest_map.show()
# how much do guests pay per night/person --------------------------------------
df['adr_pp'] = df['adr'] / df['total_guests']
df_guests = df.loc[df['is_canceled'] == 0]
room_prices = df[['hotel', 'reserved_room_type',
'adr_pp']].sort_values('reserved_room_type')
plt.figure(figsize=(8, 5))
sns.set()
def returnJsonResult():
if request.method == 'POST':
data = request.data
decodeddata = data.decode('utf-8')
jsondata = json.loads(decodeddata)
# print(jsondata)
# jsondata = {"query":"Lula",
# "country":[],
# "lang":[],
# "verified":"",
# "topic":[],
# "tweetDateFrom":"",
# "tweetDateTo":"",
# "exactMatch":"true"}
# jsondata = {"query":"modi",
# "country":["india","usa"],
# "lang":["en","hi"],
# "verified":"false",
# "topic":[],
# "tweetDateTo":"2019-08-08T00:00:00Z",
# "tweetDateFrom":"2019-09-07T00:00:00Z",
# "exactMatch":"false"}
each_query = jsondata.get('query')
each_query = each_query.replace(" ", "%20")
if (each_query == ""):
each_query = '#"*:*'
else:
# each_query = "text_hi%3A"+each_query+"%20or%20"+"text_en%3A"+each_query+"%20or%20"+"text_pt%3A"+each_query
pass
# each_query = each_query.replace(":", "\:")
# each_query = urllib.parse.quote(each_query)
# print(each_query)
input_query = each_query
ip = "18.191.55.237:8984"
# IRModel = "IRF19P1"
IRModel = "test"
#country = ["india","usa"]
country = jsondata.get('country')
lang = jsondata.get('lang') #["en","hi"]
topic = jsondata.get('topic')
#verified = "true"
verified = jsondata.get('verified')
tweet_date_from = jsondata.get('tweetDateFrom')
tweet_date_to = jsondata.get('tweetDateTo')
#http://13.59.238.116:8983/solr/IRF19P1/select?q=*%3A*&rows=20
#topic = []#["news"]
#inputQuery ="*%3A*"
exact_match = jsondata.get('exactMatch')
filter_query = ""
append = "%20OR%20"
and_append = "&fq="
#2019-09-07T00:00:00Z TO 2019-09-08T00:00:00Z
#tweet_date%3A%5B2019-09-07T00%3A00%3A00Z%20TO%202019-09-08T00%3A00%3A00Z%5D%20
if (len(country) > 0):
filter_query = "fq="
else:
filter_query = ""
if (len(country) > 0):
filter_query = filter_query + "country%3A" + country[0]
for i in range(1, len(country)):
filter_query = filter_query + append + country[i]
#if(i != len(country) -1)# or len(lang) > 0 or len(topic) > 0 or verified == "true"):
# fq = fq+append
# if(each_query != "ptshrikant"):
if (len(lang) > 0):
if (filter_query == ""):
filter_query = "fq=" + "tweet_lang%3A" + lang[0]
else:
filter_query = filter_query + and_append + "tweet_lang%3A" + lang[
0]
#if(len(lang) > 0)
# fq = fq +"tweet_lang%3A"+lang[0]
for i in range(1, len(lang)):
filter_query = filter_query + append + lang[i]
if (i != len(lang) -
1): # or len(topic) > 0 or verified == "true"):
filter_query = filter_query + append
if (len(topic) > 0):
if (filter_query == ""):
filter_query = "fq=" + "poi_name%3A" + topic[0]
else:
filter_query = filter_query + and_append + "poi_name%3A" + topic[
0]
for i in range(1, len(topic)):
filter_query = filter_query + append + topic[i]
#if(i != len(topic) -1 or verified == "true"):
# fq = fq+append
if (verified == True):
if (filter_query == ""):
filter_query = "fq=" + "verified%3Atrue"
else:
filter_query = filter_query + and_append + "verified%3Atrue"
if (verified == False):
if (filter_query == ""):
filter_query = "fq=" + "verified%3Afalse"
else:
filter_query = filter_query + and_append + "verified%3Afalse"
#2019-09-07T00:00:00Z TO 2019-09-08T00:00:00Z
#tweet_date%3A%5B2019-09-07T00%3A00%3A00Z%20TO%202019-09-08T00%3A00%3A00Z%5D%20
tweet_date_from = jsondata.get('tweetDateFrom')
tweet_date_to = jsondata.get('tweetDateTo')
if (tweet_date_from != ""):
tweet_date_from = tweet_date_from + "T00:00:00Z"
if (tweet_date_to != ""):
tweet_date_to = tweet_date_to + "T00:00:00Z"
if (tweet_date_from != "" and tweet_date_to != ""):
date_filter = tweet_date_from + " TO " + tweet_date_to
date_filter = date_filter.replace(":", "%3A")
date_filter = date_filter.replace(" ", "%20")
#print(date_filter)
date_filter = "tweet_date%3A%5B" + date_filter + "%5D%20"
#print(date_filter)
if (filter_query == ""):
filter_query = "fq=" + date_filter
else:
filter_query = filter_query + and_append + date_filter
elif (tweet_date_from != ""):
date_filter = tweet_date_from + " TO "
date_filter = date_filter.replace(":", "%3A")
date_filter = date_filter.replace(" ", "%20")
#print(date_filter)
date_filter = "tweet_date%3A%5B" + date_filter + "%20*%5D"
#print(date_filter)
if (filter_query == ""):
filter_query = "fq=" + date_filter
else:
filter_query = filter_query + and_append + date_filter
elif (tweet_date_to != ""):
#tweet_date%3A%5B*%20TO%202019-09-08T00%3A00%3A00Z%5D
date_filter = "TO " + tweet_date_to
date_filter = date_filter.replace(":", "%3A")
date_filter = date_filter.replace(" ", "%20")
#print(date_filter)
date_filter = "tweet_date%3A%5B*%20" + date_filter + "%5D"
#print(date_filter)
if (filter_query == ""):
filter_query = "fq=" + date_filter
else:
filter_query = filter_query + and_append + date_filter
# print(filter_query)
#http://18.218.221.88:8984/solr/BM25/select?defType=edismax&q=ARTIKEL&wt=json
#http://18.218.221.88:8984/solr/BM25/select?defType=edismax&q=Anti-Refugee%20Rally%20in%20Dresden&fl=id%2Cscore&wt=json&indent=true&rows=20
#http://ec2-18-219-82-180.us-east-2.compute.amazonaws.com:8984/solr/IRF19P1/select?fq=tweet_date%3A%5B2019-09-07T00%3A00%3A00Z%20TO%202019-09-08T00%3A00%3A00Z%5D%20AND%20verified%3Atrue&q=*%3A*
#tweet_date:[2019-09-07T00:00:00Z TO 2019-09-08T00:00:00Z] AND verified:true
if (exact_match):
inurl = 'http://' + ip + '/solr/' + IRModel + '/select?' + filter_query + '&q=' + input_query + '&rows=1000'
# if(jsondata.get('query') == "isro"):
# inurl = 'http://' + ip + '/solr/' + IRModel + '/select?' + filter_query + '&q='+ input_query +'&rows=124'
else:
inurl = 'http://' + ip + '/solr/' + IRModel + '/select?defType=edismax&' + filter_query + '&q=' + input_query + '&rows=1000'
print(inurl)
data = urllib.request.urlopen(inurl)
docs = json.load(data)['response']['docs']
#print(docs)
# print("length:", len(docs))
sentiment_list = dict()
sentiment_list['positive'] = 0
sentiment_list['neutral'] = 0
sentiment_list['negative'] = 0
for tweet_texts in docs:
sentiment = sentiment_analyse(tweet_texts['tweet_text'][0])
tweet_texts['sentiment'] = sentiment
sentiment_list[sentiment] = sentiment_list.get(sentiment) + 1
# print(tweet_texts)
# files = [f for f in os.listdir('.') if os.path.isfile(f)]
# for f in files:
# print(f)
# os.remove("Hashtags.html")
# os.remove("Language.html")
# os.remove("Location.html")
# os.remove("Mentions.html")
# os.remove("Sentiments.html")
# os.remove("TimeSeries.html")
# os.remove("TimeSeriesLanguage.html")
# os.remove("Topics.html")
# print("-----------------------------------------------------------------")
# files = [f for f in os.listdir('.') if os.path.isfile(f)]
# for f in files:
# print(f)
date_list = list()
lang_list = list()
country_list = list()
hashtags_list = list()
mentions_list = list()
date_lang_list = dict()
topics = dict()
for i in range(len(docs)):
try:
# date_time = docs[i].get("tweet_date")[0].find("T")
# print(date_time)
tweet_date = docs[i].get("tweet_date")[0][0:10]
date_list.append(tweet_date)
docs[i]["tweet_date"] = tweet_date
doc_tweet_lang = docs[i].get("tweet_lang")[0]
lang_list.append(doc_tweet_lang)
tweet_topic = docs[i].get("topic")[0]
if (doc_tweet_lang in date_lang_list):
date_lang_list[doc_tweet_lang].append(
docs[i].get("tweet_date")[0][0:10])
else:
date_lang_list[doc_tweet_lang] = list()
date_lang_list[doc_tweet_lang].append(
docs[i].get("tweet_date")[0][0:10])
if (tweet_topic in topics):
topics[tweet_topic] = topics.get(tweet_topic) + 1
else:
topics[tweet_topic] = 1
country_list.append(docs[i].get("country")[0])
# print(country_list)
(hashtags_list.append(docs[i].get("hashtags.text")[0])
if docs[i].get("hashtags.text")[0] is not None else None)
# if(docs[i].get("hashtags")[0]):
# hashtags_list.append(docs[i].get("hashtags")[0])
# print(hashtags_list)
# if(docs[i].get("mentions")[0]):
(mentions_list.append(docs[i].get("mentions")[0])
if docs[i].get("mentions")[0] is not None else None)
# mentions_list.append(docs[i].get("mentions")[0])
# print(mentions_list)
except:
pass
# print(date_list)
# try:
date_list = dict(Counter(date_list))
lang_list = dict(Counter(lang_list))
country_list = dict(Counter(country_list))
hashtags_list = dict(Counter(hashtags_list))
mentions_list = dict(Counter(mentions_list))
# print(len(mentions_list))
for key in date_lang_list:
date_lang_list[key] = dict(Counter(date_lang_list[key]))
# print(date_list)
# print(lang_list)
# print(country_list)
# print(hashtags_list)
# print(mentions_list)
# print(date_lang_list)
country_data = {
'country': ['United States', 'India', 'Brazil'],
'Tweets': [
country_list.get('USA'),
country_list.get('India'),
country_list.get('Brazil')
],
'country code': ['USA', 'IND', 'BRA']
}
country_df = pd.DataFrame(country_data)
fig = px.choropleth(country_df,
locations="country code",
color="Tweets",
hover_name="country",
color_continuous_scale='plasma')
# pio.show(fig)
# pio.write_html(fig, file='Location.html', default_width='370px', default_height='370px')
fig.update_layout(
title="Heatmap of count of tweets from different countries.")
pio.write_html(fig, file='Location.html')
fig = go.Figure(data=[
go.Pie(labels=list(lang_list.keys()),
values=list(lang_list.values()))
])
# pio.show(fig)
# pio.write_html(fig, file='Language.html', default_width='370px', default_height='370px')
fig.update_layout(
title="Pie chart of count of tweets in different languages")
pio.write_html(fig, file='Language.html')
date_list_key_sorted = list()
date_list_value_sorted = list()
for i in sorted(date_list.keys()):
date_list_key_sorted.append(i)
date_list_value_sorted.append(date_list.get(i))
fig = go.Figure(
go.Scatter(x=date_list_key_sorted, y=date_list_value_sorted))
fig.update_xaxes(title_text='Dates')
fig.update_yaxes(title_text='No of tweets')
fig.update_layout(title="Number of tweet on different dates")
# pio.show(fig)
# pio.write_html(fig, file='TimeSeries.html', default_width='370px', default_height='370px')
pio.write_html(fig, file='TimeSeries.html')
fig = go.Figure()
for key in date_lang_list:
date_lang_list_key_sorted = list()
date_lang_list_value_sorted = list()
for i in sorted(date_lang_list[key].keys()):
date_lang_list_key_sorted.append(i)
date_lang_list_value_sorted.append(date_lang_list[key].get(i))
fig.add_trace(
go.Scatter(
x=date_lang_list_key_sorted,
y=date_lang_list_value_sorted,
name=key,
# line_color='deepskyblue',
opacity=0.8))
# print(date_lang_list_key_sorted, date_lang_list_value_sorted)
fig.update_xaxes(title_text='Dates')
fig.update_yaxes(title_text='No of tweets')
# fig.update_layout(title={'text':"Number of tweet on different dates", 'xanchor': 'left'})
fig.update_layout(
title="Number of tweet in different languages on different dates")
# pio.write_html(fig, file='TimeSeriesLanguage.html', default_width='370px', default_height='370px')
pio.write_html(fig, file='TimeSeriesLanguage.html')
# fig.add_trace(go.Scatter(
# x=date_list_key_sorted_1,
# y=date_list_value_sorted_1,
# name="AAPL Low",
# line_color='dimgray',
# opacity=0.8))
# Use date string to set xaxis range
# fig.update_layout(xaxis_range=['2016-07-01','2016-12-31'],
# title_text="Manually Set Date Range")
# fig.show()
fig = {
"data": [{
"type": "bar",
"x": list(hashtags_list.keys()),
"y": list(hashtags_list.values())
}],
"layout": {
"title": {
"text": "Number of tweets per hashtag"
}
}
}
# fig.update_xaxes(title_text='Hashtags')
# fig.update_yaxes(title_text='No of tweets')
pio.show(fig)
# pio.write_html(fig, file='Hashtags.html', default_width='370px', default_height='370px')
pio.write_html(fig, file='Hashtags.html')
fig = {
"data": [{
"type": "bar",
"x": list(mentions_list.keys()),
"y": list(mentions_list.values())
}],
"layout": {
"title": {
"text": "Number of tweets per mention"
}
}
}
# fig.update_xaxes(title_text='Mention')
# fig.update_yaxes(title_text='No of tweets')
# pio.show(fig)
# pio.write_html(fig, file='Mentions.html', default_width='370px', default_height='370px')
pio.write_html(fig, file='Mentions.html')
# print(len(list(mentions_list.keys())))
# print(len(list(mentions_list.values())))
fig = go.Figure(data=[
go.Pie(labels=list(topics.keys()), values=list(topics.values()))
])
# pio.show(fig)
# pio.write_html(fig, file='Topics.html', default_width='370px', default_height='370px')
fig.update_layout(
title="Pie chart of count of tweets in different languages")
pio.write_html(fig, file='Topics.html')
fig = go.Figure(data=[
go.Pie(labels=list(sentiment_list.keys()),
values=list(sentiment_list.values()))
])
# pio.show(fig)
# pio.write_html(fig, file='Language.html', default_width='370px', default_height='370px')
fig.update_layout(
title="Result of sentiment analysis on the query result")
pio.write_html(fig, file='Sentiments.html')
# except:
# pass
# labels = date_list_key_sorted
# values = date_list_value_sorted
#print(docs[0])
#print()
#print(docs[1])
#print("leng",len(docs))
# print(country_df)
# del country_data
# del country_df
return json.dumps(docs)
id='treemap',
figure=px.treemap(
df,
path=['Country', 'Axis of intervention', 'Region'],
color="Country share % out of all budget",
values='Voted 2018 project budget €',
height=600,
width=1450).update_layout(margin=dict(t=25, r=0, l=5, b=20))),
dbc.Row([
dbc.Col([
dcc.Graph(id='country-map',
config={'displayModeBar': False},
figure=px.choropleth(
df,
locations="iso_alpha",
hover_name="Country",
scope='africa',
projection='natural earth').update_traces(
showlegend=False).update_layout(
margin=dict(t=25, r=0, l=5, b=20)))
],
width=6),
dbc.Col([html.Div(id='container')], width=6)
])
],
fluid=True)
@app.callback(Output("treemap", "figure"), Input("year", "value"))
def build_treemap(value):
if value == '2018':
fig = px.treemap(
}
region_color_dict = {
'Northeast': 'blue',
'South': 'red',
'Midwest': 'yellow',
'West': 'green',
'Other': 'black'
}
usa_df = pd.DataFrame({'abbrev': [k for k in region_dict]})
usa_df['region'] = [region_dict[k] for k in usa_df['abbrev']]
region_map = px.choropleth(
usa_df,
locations=[k for k in region_dict],
locationmode='USA-states',
scope='usa',
color='region',
color_discrete_map=region_color_dict,
category_orders={
'region': ['Northeast', 'South', 'Midwest', 'West', 'Other']
},
title='Symbol outlines denote region')
# here's where the magic happens
app = dash.Dash(__name__)
app.layout = html.Div(children=[
html.H1(children='stately.io'),
html.Div(children="""
Disrupting tomorrow, today!
"""),
html.Div(children="""
Figures may take a few seconds to display properly
def update_modal(data, year):
# if black frame of treemap, don't update
if data is None:
return dash.no_update
# if no currentpath or country is chosen, don't update
elif data['points'][0].get('currentPath') is None:
return dash.no_update
elif data['points'][0]['currentPath'] == '/':
if data['points'][0].get('label') is None:
return dash.no_update
else:
label_slct = data['points'][0]['label']
if year == '2018':
dff = df[df["Country"] == label_slct]
if year == '2019':
dff = df19[df19["Country"] == label_slct]
extract_country_index = dff[dff['Country'] ==
label_slct].index.values.tolist()
borders = [
1 if i in extract_country_index else 4 for i in range(len(dff))
]
# build map
fig = px.choropleth(dff,
locations="iso_alpha",
hover_name="Country",
scope='africa',
projection='natural earth').update_traces(
marker_line_width=borders,
showlegend=False).update_layout(
margin=dict(t=25, r=0, l=5, b=20))
# create the table
table_header = [html.Thead(html.Tr([html.Th(label_slct)]))]
rows = []
for x in dff["notes"]:
if pd.isnull(x):
continue
rows.append(html.Tr([html.Td(x)]))
table_body = [html.Tbody(rows)]
return fig, dbc.Table(table_header + table_body, bordered=True)
# if axis of intervention is chosen (country is parent), don't update
elif data['points'][0]['parent'] in df.Country.unique():
label_slct = data['points'][0]['label']
parent_slct = data['points'][0]['parent']
if year == '2018':
dff = df[(df["Axis of intervention"] == label_slct)
& (df["Country"] == parent_slct)]
if year == '2019':
dff = df19[(df19["Axis of intervention"] == label_slct)
& (df19["Country"] == parent_slct)]
# make selected countries' borders on map thicker
extract_country_index = dff[dff['Country'] ==
parent_slct].index.values.tolist()
borders = [
1 if i in extract_country_index else 4 for i in range(len(dff))
]
# build map
fig = px.choropleth(dff,
locations="iso_alpha",
hover_name="Country",
scope='africa',
projection='natural earth').update_traces(
marker_line_width=borders,
showlegend=False).update_layout(
margin=dict(t=25, r=0, l=5, b=20))
# create the table
table_header = [html.Thead(html.Tr([html.Th(label_slct)]))]
rows = []
for x in dff["notes"]:
if pd.isnull(x):
continue
rows.append(html.Tr([html.Td(x)]))
table_body = [html.Tbody(rows)]
return fig, dbc.Table(table_header + table_body, bordered=True)
# if Region is chosen, build table
else:
label_slct = data['points'][0]['label']
parent_slct = data['points'][0]['parent']
print(label_slct), print(parent_slct), print(data)
if year == '2018':
dff = df[(df.Region == label_slct)
& (df["Axis of intervention"] == parent_slct)]
if year == '2019':
dff = df19[(df19.Region == label_slct)
& (df19["Axis of intervention"] == parent_slct)]
# make selected countries' borders on map thicker
extract_country = data['points'][0]['currentPath']
extract_country = extract_country.split('/')[1]
extract_country_index = dff[dff['Country'] ==
extract_country].index.values.tolist()
borders = [
1 if i in extract_country_index else 4 for i in range(len(dff))
]
# build map
fig = px.choropleth(dff,
locations="iso_alpha",
hover_name="Country",
scope='africa',
projection='natural earth').update_traces(
marker_line_width=borders,
showlegend=False).update_layout(
margin=dict(t=25, r=0, l=5, b=20))
# create the table
table_header = [html.Thead(html.Tr([html.Th(label_slct)]))]
rows = []
for x in dff["notes"]:
if pd.isnull(x):
continue
rows.append(html.Tr([html.Td(x)]))
table_body = [html.Tbody(rows)]
return fig, dbc.Table(table_header + table_body, bordered=True)
# creating another map wich animates the spread of the virus
fig2 = px.scatter_geo(df,
locations='countryCode',
color='continent',
hover_name='country',
size='cases',
projection="natural earth",
title='World COVID-19 Cases Animation',
animation_frame="date")
# fig.show()
# creating an animated map where we can see how many people die of covid-19
fig3 = px.choropleth(df,
locations="countryCode",
color="deaths",
hover_name="country",
animation_frame="date",
range_color=[0, 2500])
'''
Since the data is in a time-series format, i decided to make accumulated data
so that i can show total deaths and cases.
'''
total_list = df.groupby('countryCode')['deaths'].sum().tolist()
country_list = df["countryCode"].tolist()
country_set = set(country_list)
country_list = list(country_set)
country_list.sort()
new_df = pd.DataFrame(list(zip(country_list, total_list)),
columns=['countryCode', 'deaths'])
# Import plotly express library for the line graph
import plotly.express as px
# The following code till Line 38 is the code for the line graph
grp = cases.groupby(['ObservationDate', 'Country/Region'])['Confirmed', 'Deaths', 'Recovered'].max()
grp = grp.reset_index()
grp['Date'] = pd.to_datetime(grp['ObservationDate'])
grp['Date'] = grp['Date'].dt.strftime('%m/%d/%Y')
grp['Active'] = grp['Confirmed'] - grp['Recovered'] - grp['Deaths']
grp['Country'] = grp['Country/Region']
fig = px.choropleth(grp, locations="Country", locationmode='country names',
color="Confirmed",
hover_name="Country/Region",
hover_data = [grp.Recovered,grp.Deaths,grp.Active],
projection="mercator",
animation_frame="Date",width=1000, height=700,
color_continuous_scale='Reds',
range_color=[1000,50000],
title='World Map of Coronavirus Confirmed Cases')
fig.update(layout_coloraxis_showscale=True)
# Set the variable for the us covid cases
us_covid = pd.read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-counties.csv", header = 0,
dtype={"fips": str}, parse_dates=[0])
# Unique method to classify state
us_covid['state'].unique()
# Query method to define the desired states from the dataset
us_covid_ne = us_covid.query('state == ["Connecticut", "Maine", "Massachusetts", "New Hampshire", "Rhode Island", "Vermont", "New Jersey", "New York", "Pennsylvania"]')
with urlopen(
'https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json'
) as response:
counties = json.load(response)
import pandas as pd
df = pd.read_csv(
"https://raw.githubusercontent.com/plotly/datasets/master/fips-unemp-16.csv",
dtype={"fips": str})
import plotly.express as px
fig = px.choropleth(df,
geojson=counties,
locations='fips',
color='unemp',
color_continuous_scale="Viridis",
range_color=(0, 12),
scope="usa",
labels={'unemp': 'unemployment rate'})
fig.update_layout(margin={"r": 0, "t": 0, "l": 0, "b": 0})
from flask import Flask, render_template, url_for
import dash
import dash_core_components as dcc
import dash_html_components as html
server = Flask(__name__)
@server.route('/')
def index():
def fig_a002():
# -- PHARMA
pharma = (
prep_salutegov.parse_dataset("pharmacies")
.groupby("region_code")[["pharmacy_code"]]
.nunique()
.reset_index()
.rename(columns={"pharmacy_code": "n_pharmacies"})
)
asl = (
prep_salutegov.parse_dataset("asl_comuni_pop")
.replace("", np.nan)
.dropna(subset=["region_code"])
)
asl["TOTALE"] = (
asl["TOTALE"]
.str.replace(".", "")
.str.replace(",", ".")
.replace("", np.nan)
.astype(float)
)
pop = asl.groupby(["region_code"]).agg(
population=pd.NamedAgg("TOTALE", "sum"),
region=pd.NamedAgg("region", "first"),
)
pharma["population"] = pop.reindex(pharma["region_code"].values)[
"population"
].values
pharma["region"] = (
pop.reindex(pharma["region_code"].values)["region"].str.title().values
)
pharma.loc[
pharma.region_code == "04", "region"
] = "Trentino-Alto Adige/Südtirol"
pharma["hab_per_pharma"] = (
(pharma["population"] / pharma["n_pharmacies"]).round(0).astype(int)
)
fig_a002 = px.choropleth(
pharma,
geojson=GDF_REG,
color="hab_per_pharma",
hover_data=["region", "n_pharmacies", "population"],
locations="region_code",
# range_color=(0, 3.5),
center={"lat": 42.65, "lon": 12.4},
featureidkey="properties.reg_istat_code",
projection="mercator",
template="plotly_white",
color_continuous_scale=px.colors.diverging.Temps,
labels={
"region_code": "Cod. Regione",
"region": "Regione",
"hab_per_pharma": "Ab. per Farmacia",
"n_pharmacies": "Numero Farmacie",
"population": "Numero Abitanti",
},
# line_shape="spline",
)
fig_a002.update_geos(fitbounds="locations", visible=False).update_layout(
width=600, height=600
)
fig_a002.update_layout(
margin={"l": 80, "r": 140, "b": 80, "t": 100, "autoexpand": False},
title=dict(
text="<br><b>Abitanti per Farmacia</b></br>"
'<span style="font-size: 11px;">Anno 2018 - Meno è Meglio</span>',
x=0.5,
y=0.96,
),
xaxis=dict(title=None),
yaxis_tickformat="20",
legend=dict(orientation="h", yanchor="top", y=-0.15, title=None),
# showlegend=False,
annotations=[
dict(
text="Fonte: Rielaborazione BuildNN & Tortuga da Ministero "
"della Salute",
font=dict(size=9, color="grey"),
showarrow=False,
xref="paper",
yref="paper",
y=-0.0,
)
],
)
watermark(fig_a002)
return fig_a002
%load_ext google.colab.data_table
import pandas as pd
url="https://raw.githubusercontent.com/marelly1/pandas/master/totalescv.csv"
import pandas as pd
url="https://raw.githubusercontent.com/marelly1/pandas/master/totalescv.csv"
df=pd.read_csv(url)
df=df.T
df=df.drop(["date"])
df=df.reset_index()
df=df.rename({"index":"Paises",53:"Total"},axis=1)
print(list(df))
#se debe instalar por el cmd de windows
#pip install pycountry
import pycountry
def get_alph_3(location):
try:
return pycountry.countries.get(name=location).alpha_3
except:
return None
df["Code"]=df["Paises"].apply(lambda x: get_alph_3(x))
print(df.head(6))
import plotly.express as px
fig = px.choropleth(df,locations="Code",color="Total",hover_name="Paises",color_continuous_scale=px.colors.sequential.Plasma)
fig.show()
def eligible_map_func(elig_data, dose):
fig = px.choropleth(
elig_data,
geojson=jdata,
locations="id",
color=elig_data["Procent vaccinerade"],
# Below gives discrete colours for ranges
color_continuous_scale=[
(splits[0], map_colour[10]),
(splits[1], map_colour[10]),
(splits[1], map_colour[9]),
(splits[2], map_colour[9]),
(splits[2], map_colour[8]),
(splits[3], map_colour[8]),
(splits[3], map_colour[7]),
(splits[4], map_colour[7]),
(splits[4], map_colour[6]),
(splits[5], map_colour[6]),
(splits[5], map_colour[5]),
(splits[6], map_colour[5]),
(splits[6], map_colour[4]),
(splits[7], map_colour[4]),
(splits[7], map_colour[3]),
(splits[8], map_colour[3]),
(splits[8], map_colour[2]),
(splits[9], map_colour[2]),
(splits[9], map_colour[1]),
(splits[10], map_colour[1]),
],
# this keeps the range of colours constant regardless of data
range_color=[0, 100],
scope="europe",
hover_name="Region",
hover_data={
"Procent vaccinerade": ":.2f",
"Vaccinationsstatus": True,
"id": False,
},
labels={
"Procent vaccinerade":
"Percentage of eligible<br>population vaccinated (%)",
"Vaccinationsstatus": "<br>Number of Doses",
},
)
# this section deals with the exact focus on the map
fig.update_layout(geo=dict(
lonaxis_range=[20, 90], # the logitudinal range to consider
lataxis_range=[48, 100], # the logitudinal range to consider
projection_scale=4.55, # this is kind of like zoom
center=dict(lat=lat_foc, lon=lon_foc), # this will center on the point
visible=False,
))
fig.update_layout(margin={"r": 0, "t": 0, "l": 0, "b": 0})
fig.update_layout(dragmode=False)
# The below labels the colourbar categories
fig.update_layout(
coloraxis_colorbar=dict(
title="<b>Percentage of eligible<br>population vaccinated with<br>"
+ dose + "</b>",
tickvals=[5, 15, 25, 35, 45, 55, 65, 75, 85, 95],
ticktext=[
"00.00 - 9.99%",
"10.00 - 19.99%",
"20.00 - 29.99%",
"30.00 - 39.99%",
"40.00 - 49.99%",
"50.00 - 59.99%",
"60.00 - 69.99%",
"70.00 - 79.99%",
"80.00 - 89.99%",
"90.00 - 100.00%",
],
x=0.51,
y=0.40,
thicknessmode="pixels",
thickness=10,
lenmode="pixels",
len=285,
),
font=dict(size=12),
)
fig.update_traces(marker_line_color="white")
# fig.show()
filename = os.path.join(os.getcwd(), "vaccine_plots",
"{}_elig_map.json".format(name.replace(" ", "")))
if not os.path.isdir(os.path.dirname(filename)):
os.mkdir(os.path.dirname(filename))
fig.write_json(filename)
------------------------------------------------------------------------------------------------------------------------------------------------------
'''
path = 'https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-07-2020.csv'
df = pd.read_csv(path)
df.drop(['FIPS', 'Admin2', 'Last_Update', 'Province_State', 'Combined_Key'],
axis=1,
inplace=True)
df.rename(columns={'Country_Region': "Country"}, inplace=True)
world = df.groupby("Country")['Confirmed', 'Active', 'Recovered',
'Deaths'].sum().reset_index()
figure = px.choropleth(world,
locations="Country",
locationmode="country names",
color="Confirmed",
hover_name="Country",
color_continuous_scale="tealgrn",
range_color=[1, 10000000],
title="Countries with Confirmed cases")
tabControl = ttk.Notebook(root)
tab1 = ttk.Frame(tabControl)
tabControl.add(tab1, text='CovidView')
tab2 = ttk.Frame(tabControl)
tabControl.add(tab2, text='Covid19 Map')
tab3 = ttk.Frame(tabControl)
tabControl.add(tab3, text="Advice-O-Bot")
def generate_map(df):
df = rename(df)
df['POS'] = df['County'] + ', ' + df['StateName']
maps = []
with urlopen(
'https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json'
) as response:
counties = json.load(response)
for key in keys:
fig = px.choropleth(
df,
geojson=counties,
locations='countyFIPS',
color=np.log(df[key] + 1),
color_continuous_scale=[
'#F7E8E4', '#F5C8BB', '#B96D67', '#A83C3B', '#8B2222',
'#5B0D0D', '#5A2318'
],
scope="usa",
hover_data=[
'State', 'County', 'Cumulative Cases', 'New Cases',
'Cumulative Deaths', 'New Deaths', 'Deaths per 100k',
'Cases per 100k', 'New Cases per 100k', 'New Deaths per 100k'
],
title=key + ' on ' +
(datetime.today() - timedelta(days=1)).strftime('%m-%d'))
fig.update_layout(coloraxis_colorbar=dict(
len=0.75,
title=key,
tickvals=[
2.302585092994046, 4.605170185988092, 6.907755278982137,
9.210340371976184, 11.512925464970229
],
ticktext=['10', '100', '1k', '10k', '100k', '1000k'],
x=1,
y=0.5))
## update the hover information
for c in ["countyFIPS=%{location}<br>", "<br>color=%{z}"]:
fig['data'][0]['hovertemplate'] = fig['data'][0][
'hovertemplate'].replace(c, "")
fig['data'][0]['hovertemplate'] = fig['data'][0][
'hovertemplate'].replace("=", ": ")
fig.update_layout(margin={"r": 0, "t": 40, "l": 0, "b": 0})
fig.update_layout(
paper_bgcolor='rgb(0,0,0)',
plot_bgcolor='rgb(0,0,0)',
template='plotly_dark',
)
fig['layout'].update(width=900, height=450, autosize=True, title_x=0.3)
if key == 'Cumulative Cases':
fig.write_image(oj(parentdir, "results/search_map.svg"),
width=900,
height=450)
maps.append(
plotly.offline.plot(fig, include_plotlyjs=False,
output_type='div'))
df_tab = df.sort_values(by=key, ascending=False)
df_tab = df_tab.reset_index(drop=True)[['POS', key]].loc[:19, :]
fig = go.Figure(data=[
go.Table(header=dict(values=['', 'County', key],
line_color='grey',
fill_color='darkgrey',
font_color='white',
font_size=12,
align='center'),
cells=dict(values=[[i + 1 for i in range(len(df_tab))],
df_tab['POS'], df_tab[key]],
line_color='darkgrey',
fill_color='grey',
font_color='white',
font_size=11,
align='center'),
columnwidth=[20, 120, 80])
])
fig['layout'].update(paper_bgcolor='rgb(0,0,0)',
plot_bgcolor='rgb(0,0,0)',
margin=dict(l=0, r=0, t=0, b=0),
width=200,
height=550,
autosize=True,
template='plotly_dark')
fig.write_image(oj(parentdir, "results/" + key + ".svg"),
width=200,
height=550)
print('succesfully generated search map')
return maps