# In[3]:
"""create a heatmap of daily total steps burned"""
allFiles = glob.glob("Data/Activities_Summary/*.csv") # create a list of all data files
fulldf = []
for file_ in allFiles: # for loop to merge data files
df = pd.read_csv(str(file_), index_col=0)
fulldf.append(df)
fulldf = pd.concat(fulldf)
fulldf.index=pd.to_datetime(fulldf.index) # use date as index
fulldf = fulldf[fulldf.steps != 0] # remove days without data
events = pd.Series(fulldf['steps'])
# create a heat map of steps walked per day
fig,ax=calmap.calendarplot(events, monthticks=True, cmap='GnBu', vmin=0, vmax=max(fulldf['steps'])+1000,
fillcolor='gainsboro', linecolor='white', linewidth=2,
fig_kws=dict(figsize=(12, 8)));
cax = fig.add_axes([1.0, 0.2, 0.02, 0.6])
norm1 = mpl.colors.Normalize(0,max(fulldf['steps'])+1000)
cb = mpl.colorbar.ColorbarBase(cax, cmap='GnBu', norm=norm1, spacing='proportional')
cb.set_label('# of Steps')
# In[4]:
dayofweek = []
for day in fulldf.index: # create new column for day of week
#datentime=dt.datetime.strptime(day, '%Y-%m-%d')
#dateonly=datentime.date()
dateonly=day.date()
def calendar_plot_by_year(series_to_plot, normalize_each_year=False):
"""Creates a calendar heatmap of of data contained in a Series
Arg:
series_to_plot: Pandas Series object [index = dates]
normalize_each_year: Boolean flag to separately color each year
"""
# calculate number of years
start_year = series_to_plot.sort_index().index[0].year
end_year = series_to_plot.sort_index().index[-1].year
num_years = end_year - start_year + 1
# send directly to function if we want to few heatmap across full time period
if not normalize_each_year:
calmap.calendarplot(series_to_plot, cmap='YlGn', fillcolor='grey', \
linewidth=.05, daylabels=['M', 'T', 'W', 'T', 'F', 'S', 'S'], \
fig_kws=dict(figsize=(12, 2*num_years)))
return
# plot each year and build figure
fig = plt.figure(figsize=(12, 2 * num_years))
for i, year in enumerate(range(start_year, end_year + 1), 1):
year_to_plot = series_to_plot[series_to_plot.index.year == year]
# plot
axes = fig.add_subplot(num_years, 1, i)
calmap.yearplot(year_to_plot, year=year, cmap='YlGn', fillcolor='grey', linewidth=.05, \
daylabels=['M', 'T', 'W', 'T', 'F', 'S', 'S'], ax=axes)
axes.set_ylabel(year)
def create_dfs():
try:
df = pd.read_pickle("./castellion_stats.pkl")
df2 = pd.read_pickle("./castellion_winloss.pkl")
except:
df = pd.DataFrame({'Date': today, 'Count': 1}, index=[0])
df2 = pd.DataFrame({'Wins': 0, 'Games': 1}, index=[0])
dates = [today]
if df.Date.isin(dates).any():
df.loc[df.Date.isin(dates), 'Count'] += 1
else:
df = df.append({'Date': today, 'Count': 1}, ignore_index=True)
df2['Games'][0] += 1
print(df2['Games'])
df['Date'] = pd.to_datetime(df['Date'])
df.to_pickle("./castellion_stats.pkl")
df2.to_pickle("./castellion_winloss.pkl")
df.set_index('Date', inplace=True)
plt.figure(figsize=(16, 10), dpi=80)
calmap.calendarplot(df['2021']['Count'],
fig_kws={'figsize': (16, 10)},
yearlabel_kws={
'color': 'black',
'fontsize': 14
},
subplot_kws={'title': 'Days Played'},
cmap='YlOrRd')
plt.savefig('heatmap.png', bbox_inches='tight')
return df2
def calmap():
if os.path.exists(
os.path.join(root_path, "Daily Data", "Portfolio",
"Portfolio_Returns.csv")):
port_rets = pd.read_csv(os.path.join(root_path, "Daily Data",
"Portfolio",
"Portfolio_Returns.csv"),
index_col=0)
import numpy as np
np.random.seed(sum(map(ord, 'calmap')))
import calmap
events = port_rets['Portfolio Value']
events.index = pd.to_datetime(events.index)
#calmap.yearplot(events, year=2018)
calmap.calendarplot(events,
monthticks=3,
daylabels='MTWTFSS',
dayticks=[0, 2, 4, 6],
cmap='YlGn',
fillcolor='grey',
linewidth=0,
fig_kws=dict(figsize=(8, 4)))
plt.show()
else:
print(
'You have not downloaded data for your portfolio yet in oder for the optimization module to be run. Please download the data by running the following function --- port_data.portfolio_daily_data()'
)
def _plot_calendar(events, cmap="Reds", fillcolor="whitesmoke", **kwargs):
import calmap
# Filter away journal entries and sort
events = list(sorted(filter(lambda e: e.type == "data", events)))
for e in events:
e.data["substance"] = "Any"
period_counts = _count_doses(events, one_per_day=True, monthly=False)
assert len(period_counts) == 1
doses = [n_dose for n_dose in next(iter(period_counts.values())).values()]
labels = [
pd.Timestamp("-".join(map(str, date))) for sd in period_counts
for date in period_counts[sd].keys()
]
series = pd.Series(doses, index=labels)
series = series[~series.index.duplicated()]
series = series.resample("D").sum().asfreq("D")
# print(series.tail(20))
calmap.calendarplot(series,
fillcolor=fillcolor,
cmap=cmap,
linewidth=1,
fig_kws=kwargs)
plt.show()
def plot_calendar(df, habitname, show=True, year=None):
df = df[df.index.get_level_values("HabitName").isin([habitname])].reset_index()
df = df.set_index(pd.DatetimeIndex(df["CalendarDate"]))
if year:
calmap.yearplot(df["Value"], year=year)
else:
calmap.calendarplot(df["Value"])
if show:
plt.show()
def calendarImg(dataset):
for i, id_input in enumerate(dataset.id):
df = calendarDF[calendarDF.listing_id.isin([id_input])]
df['available_num'] =[3 if x ==1 else -1 for x in df['available']] # instead of t and f, it will be 3 and -1
df['date'] = pd.to_datetime(df['date'], format='%Y-%m-%d').dt.strftime('%Y-%m-%d %H:%M:%S') # convert date format with h:m:s
events=pd.Series(df['available_num']) # convert the dataset into series
events.index= pd.DatetimeIndex(df['date']) # set date as the index
calmap.calendarplot(events, monthticks=1, daylabels='MTWTFSS',cmap='YlGn', fillcolor='grey', linewidth=1, fig_kws=dict(figsize=(16, 4)))
name = "img"+str(i)+".png"
plt.savefig(name)
def Calendar_Heat_Map(self):
df = pd.read_csv("dataVset/yahoo.csv", parse_dates=['date'])
df.set_index('date', inplace=True)
# Plot
# plt.figure(figsize=(16, 10), dpi=80)
calmap.calendarplot(df['2014']['VIX.Close'],
fig_kws={'figsize': (16, 10)},
yearlabel_kws={
'color': 'black',
'fontsize': 14
},
subplot_kws={'title': 'Yahoo Stock Prices'})
plt.show()
def plot_calmap(events=_get_random_events()):
# cmap choices: viridis
calmap.calendarplot(
events,
monthticks=True,
daylabels="MTWTFSS",
cmap="PuBuGn",
fillcolor="whitesmoke",
linewidth=1,
vmin=0,
fig_kws=dict(figsize=(12, 6)),
fig_suptitle="CTimer clock count",
)
plt.show()
def calendar_plot(overall_dict, dates, filename):
names = list(overall_dict.keys())
weights = [i + 1 for i in range(len(names))]
daily_weights = list()
for day_index in range(len(dates)):
min = 999999
weight = None
for name in names:
if overall_dict[name][day_index] is not None:
if overall_dict[name][day_index] < min:
min = overall_dict[name][day_index]
weight = weights[names.index(name)]
elif overall_dict[name][day_index] == min:
weight = 0
daily_weights.append(weight)
datetimes = [
dt.datetime(year=int(date.split('/')[2]),
month=int(date.split('/')[0]),
day=int(date.split('/')[1])) for date in dates
]
series = pd.Series(data=daily_weights, index=datetimes)
cmap = matplotlib.colors.ListedColormap(
['grey', 'skyblue', 'navajowhite', 'palegreen', 'lightcoral', 'plum'])
fig, ax = calmap.calendarplot(series,
fillcolor='silver',
cmap=cmap,
fig_kws=dict(figsize=(10, 4)))
labels = ['Tie'] + names
formatter = plt.FuncFormatter(lambda val, loc: labels[int(val)])
fig.colorbar(ax[0].get_children()[1],
ax=ax.ravel().tolist(),
shrink=0.4,
format=formatter)
plt.savefig(filename)
plt.close('all')
def plot_yoy_growth(self):
# CALENDAR MAP IMAGE
calmap.calendarplot(
self.yoy_growth.iloc[self.yoy_growth.index.year > 2016]['index'],
monthticks=1,
daylabels='MTWTF',
dayticks=[0, 2, 4],
cmap='RdYlGn',
linewidth=0.2,
yearascending=False,
yearlabel_kws=dict(color='#696969'),
fig_kws=dict(figsize=(12, 8)))
plt.savefig('assets/yoy_calmap.png')
# YOY GROWTH - show different colour for positive and negative yoy growth
postive_growth = go.Scatter(
y=[0 if x < 0 else x for x in self.yoy_growth['28dayMA']],
x=self.yoy_growth.index,
fill='tozeroy',
line=dict(color='#2F80ED'))
negative_growth = go.Scatter(
y=[0 if x > 0 else x for x in self.yoy_growth['28dayMA']],
x=self.yoy_growth.index,
fill='tozeroy')
baseline = go.Scatter(y=[0 for x in self.yoy_growth.index],
x=self.yoy_growth.index,
line=dict(color='black'))
layout = go.Layout(plot_bgcolor='#ffffff',
yaxis=dict(tickformat="%"),
xaxis=dict(range=([
self.yoy_growth.index.min(),
self.yoy_growth.index.max() +
pd.DateOffset(months=6)
])),
showlegend=False,
hovermode='x')
yoy_growth_chart = go.Figure(
data=[postive_growth, negative_growth, baseline], layout=layout)
return yoy_growth_chart
def calheatmap(year):
'''
Plot a Calendar heat map. Number of citations vs Date in a specific year
Input:
year: year in [2015, 2016, 2017, 2018]
'''
assert year in [2015, 2016, 2017, 2018]
df = pd.read_csv(str(year) + 'parking-citations.csv',
parse_dates=['Issue Date'])
gp = df['Fine amount'].groupby(df['Issue Date'])
calmap.calendarplot(
gp.count(),
fig_kws={'figsize': (16, 10)},
yearlabels=False,
subplot_kws={'title': 'Number of Citations in Year ' + str(year)})
plt.show()
def plotCalendar(df):
for column in df.columns:
# https://pythonhosted.org/calmap/
fig, ax = calmap.calendarplot(
df[column], daylabels='MTWTFSS',
cmap='RdYlGn') #The _r at the end inverts the map, so 1 is green.
plt.title(column)
plt.legend()
plt.savefig(column + '.png')
return
def calmap(port_rets):
import numpy as np
np.random.seed(sum(map(ord, 'calmap')))
import calmap
events = port_rets['Portfolio Value']
events.index = pd.to_datetime(events.index)
#calmap.yearplot(events, year=2018)
calmap.calendarplot(events,
monthticks=3,
daylabels='MTWTFSS',
dayticks=[0, 2, 4, 6],
cmap='YlGn',
fillcolor='grey',
linewidth=0,
fig_kws=dict(figsize=(8, 4)))
plt.show()
def plot_daily_flow_rate_average(
df: pd.DataFrame,
factory: str,
flare: str,
max_rates: MaxRateCollection,
bound_scale: bool,
filter_run: dict = None,
**kwargs
) -> Optional[Plot]:
"""Plot heat-map for flare's average hourly flow rate per-day"""
if is_skip_plot(dict(type='plot_daily_flow_rate_average', factory=factory, flare=flare), filter_run):
return None
max_hourly_rate = max_rates.hourly if max_rates else None
if bound_scale and not max_hourly_rate:
# Bounded plot can only be made on hourly-limited flare
return None
# Build title
flare_title = get_flare_title(flare, factory)
title = f'ממוצע יומי של ספיקה שעתית {flare_title}'
title += '\nביחידות ק"ג/שעה'
if not max_hourly_rate:
title += f' {NO_LAW_STR}'
elif not bound_scale:
title += f' {law_str_unbounded_func(max_hourly_rate.rate)}'
else:
title += f' {law_str_func(max_hourly_rate.rate)}'
# Plot graph
num_years = len(df.sum(axis=1).resample('Y').sum()) # there must be a more elegant way to do this!
fig, axes = calmap.calendarplot(
df[flare],
how='mean', # Hourly
vmax=max_hourly_rate.rate if bound_scale else None,
fillcolor='grey',
linewidth=0,
fig_kws=dict(figsize=(15, 2 + 3 * num_years)),
cmap=kwargs.pop('cmap', plt.cm.get_cmap(colormap_negative_name)),
**kwargs
)
fig.suptitle(get_display(title), fontsize=30)
# Plot color bar
fig.colorbar(axes[0].get_children()[1],
ax=axes.ravel().tolist(),
orientation='horizontal',
shrink=1.0,
extend='max' if bound_scale else 'neither'
)
return Plot(fig, title, df)
def main():
df = (pd.read_excel('Growth_Without_Goals.xlsx',
sheetname='Log')).set_index('Date')
for column in df.columns:
# https://pythonhosted.org/calmap/
fig, ax = calmap.calendarplot(df[column],
daylabels='MTWTFSS',
cmap='RdYlGn')
plt.title(column)
plt.savefig(column + '.png')
def calplot_funk(df, keycol, filename_base):
'''docstring for calplot_funk function'''
fig, ax = calmap.calendarplot(
df[keycol],
fillcolor='grey', # linewidth=0,#cmap='RdYlGn',
fig_kws=dict(figsize=(17, 12)),
subplot_kws={'title': keycol},
vmin=0)
fig.colorbar(ax[0].get_children()[1],
ax=ax.ravel().tolist(),
orientation='horizontal')
filename = filename_base + '_' + keycol + '.png'
plt.savefig(filename)
return plt.show()
def calendarPlot():
import calmap
df = pd.read_csv(
"https://raw.githubusercontent.com/swapnilsaurav/Dataset/master/stock_price.csv"
)
# Prepare the data for plotting
# print("df= \n", df)
df["date"] = pd.to_datetime(df["date"])
# print("df[date]\n", df["date"])
# The data must be a series with a date time index
df.set_index("date", inplace=True)
x = df[df["year"] == 2016]["Close"]
print("x=\n", x)
# Plot the data using calmap
calmap.calendarplot(x,
fig_kws={'figsize': (16, 10)},
yearlabel_kws={
"color": "black",
"fontsize": 14
},
subplot_kws={"title": "Stock Prices"})
plt.show()
def calmap(portfolio):
port_rets = pd.read_csv(root_path + '/Daily_Data/Portfolio/' +
portfolio.Portfolio_Name +
'_Portfolio_Returns.csv',
index_col=0)
import numpy as np
np.random.seed(sum(map(ord, 'calmap')))
import calmap
events = port_rets['Portfolio Value']
events.index = pd.to_datetime(events.index)
#calmap.yearplot(events, year=2018)
calmap.calendarplot(events,
monthticks=3,
daylabels='MTWTFSS',
dayticks=[0, 2, 4, 6],
cmap='YlGn',
fillcolor='grey',
linewidth=0,
fig_kws=dict(figsize=(8, 4)))
plt.show()
def plot_daily_number_of_exceptions_from_allowed_hourly_flow_rate_average(
df: pd.DataFrame,
factory: str,
max_rates: Optional[MaxRateCollection],
filter_run: dict = None,
**kwargs
) -> Optional[Plot]:
"""Plot heat-map for number of exceptions per-day"""
if is_skip_plot(dict(type='plot_daily_number_of_exceptions_from_allowed_hourly_flow_rate_average',
factory=factory, flare=None), filter_run):
return None
if not max_rates:
return None
max_hourly_rate = max_rates.hourly
if not max_hourly_rate:
return None
max_total_hourly_rate = max_hourly_rate.rate
df = df.copy()
df['Exception'] = df['Total'] > max_total_hourly_rate
num_years = len(df.sum(axis=1).resample('Y').sum()) # there must be a more elegant way to do this!
fig, axes = calmap.calendarplot(
df['Exception'],
fillcolor='grey',
linewidth=0,
fig_kws=dict(figsize=(15, 3 + 3 * num_years)),
cmap=kwargs.pop('cmap', plt.cm.get_cmap(colormap_negative_name, 24)),
**kwargs
)
cbar = fig.colorbar(axes[0].get_children()[1],
ax=axes.ravel().tolist(),
orientation='horizontal',
shrink=1.0,
ticks=[0, 6, 12, 18, 24])
# cbar.ax.get_yaxis().labelpad = 15
cbar.ax.set_xlabel(get_display('שעות חריגה ביום'), fontsize=20)
title = f'כמות חריגות יומיות מהיתר ספיקה שעתית בלפידי {factory}'
title += '\nביחידות שעות חריגה ליום'
fig.suptitle(get_display(title), fontsize=30)
return Plot(fig, title, df)
def plot_calendar_heatmap(data,
width=800,
height=200,
style='whitegrid',
format=SVG,
cache=True):
fig, ax = calmap.calendarplot(data,
how=None,
dayticks=(0, 2, 4, 6),
yearlabel_kws={
'color': 'black',
'fontsize': 10,
'fontweight': 'normal'
},
cmap='YlGn',
fillcolor='#eeeeee')
return fig, width, height * len(data.index.year.unique())
def heatmap_data(data1, data2, data3):
value1 = []
all_day = pd.date_range('01/01/2017', periods=1095, freq='1D')
for i in range(365):
value1.append(data1["Value"][i])
for i in range(365):
value1.append(data2["Value"][i])
for i in range(365):
value1.append(data3["Value"][i])
events = pd.Series(value1, index=all_day)
fig, ax = calmap.calendarplot(events,
linewidth=0,
fig_kws=dict(figsize=(17, 8)))
fig.colorbar(ax[0].get_children()[1], ax=ax.ravel().tolist())
plt.show(fig)
numPerDay = 0
else:
numPerDay = numPerDay + 1
print(nArr)
newArray = np.asarray(nArr)
print(newArray)
df = pd.DataFrame({'Date': newArray[:, 0], 'AppNum': newArray[:, 1]})
print(df)
df.set_index('Date', inplace=True)
# Plot
plt.figure(figsize=(16, 10), dpi=80)
calmap.calendarplot(df[year[i]]['AppNum'],
fig_kws={'figsize': (16, 10)},
yearlabel_kws={
'color': 'black',
'fontsize': 14
},
subplot_kws={
'title':
'{} Diligence of Sending Applications'.format(
year[i])
})
plt.show()
allFiles = glob.glob(
"Data/Activities_Summary/*.csv") # create a list of all data files
fulldf = []
for file_ in allFiles: # for loop to merge data files
df = pd.read_csv(str(file_), index_col=0)
fulldf.append(df)
fulldf = pd.concat(fulldf)
fulldf.index = pd.to_datetime(fulldf.index) # use date as index
fulldf = fulldf[fulldf.steps != 0] # remove days without data
events = pd.Series(fulldf['steps'])
# create a heat map of steps walked per day
fig, ax = calmap.calendarplot(events,
monthticks=True,
cmap='GnBu',
vmin=0,
vmax=max(fulldf['steps']) + 1000,
fillcolor='gainsboro',
linecolor='white',
linewidth=2,
fig_kws=dict(figsize=(12, 8)))
cax = fig.add_axes([1.0, 0.2, 0.02, 0.6])
norm1 = mpl.colors.Normalize(0, max(fulldf['steps']) + 1000)
cb = mpl.colorbar.ColorbarBase(cax,
cmap='GnBu',
norm=norm1,
spacing='proportional')
cb.set_label('# of Steps')
# In[4]:
dayofweek = []
# -*- coding: utf-8 -*-
"""
Created on Sat Nov 30 20:15:47 2019
@author: Jie Zhang，微信公众号【EasyShu】，本代码源自《Python数据可视化之美》
"""
import pandas as pd
import numpy as np
from plotnine import *
import matplotlib.pyplot as plt
import calmap
df = pd.read_csv('Calendar.csv', parse_dates=['date'])
df.set_index('date', inplace=True)
fig, ax = calmap.calendarplot(df['value'],
fillcolor='grey',
linecolor='w',
linewidth=0.1,
cmap='RdYlGn',
yearlabel_kws={
'color': 'black',
'fontsize': 12
},
fig_kws=dict(figsize=(10, 5), dpi=80))
fig.colorbar(ax[0].get_children()[1], ax=ax.ravel().tolist())
plt.show()
#fig.savefig('日历图1.pdf')
# https://pythonhosted.org/calmap/
import calmap
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
np.random.seed(sum(map(ord, 'calmap')))
all_days = pd.date_range('1/15/2014', periods=700, freq='D')
days = np.random.choice(all_days, 500)
events = pd.Series(np.random.randn(len(days)), index=days)
calmap.calendarplot(events,
monthticks=3,
daylabels='MTWTFSS',
dayticks=[0, 2, 4, 6],
cmap='YlGn',
fillcolor='grey',
linewidth=0,
fig_kws=dict(figsize=(8, 4)))
plt.show()
# https://github.com/martijnvermaat/calmap
# http://stackoverflow.com/a/11274226
# http://pandas.pydata.org/pandas-docs/version/0.17.0/generated/pandas.Series.from_csv.html
# http://pandas.pydata.org/pandas-docs/version/0.17.1/generated/pandas.DataFrame.sort_index.html
import os
# generating matplotlib graphs without a x-server
# http://stackoverflow.com/a/4935945
import matplotlib as mpl
mpl.use('Agg')
import calmap
import matplotlib.pyplot as plt
import pandas
csv_file = os.getcwd() + "/../data/steps-count.csv"
events = pandas.Series.from_csv(csv_file)
events = events.sort_index(ascending=False)
ax = calmap.calendarplot(events, yearascending=False, daylabels='mtwtfss',
linewidth=0.5, vmax=10000, vmin=1, cmap='Greens',
fig_kws=dict(figsize=(8, 4)))
plt.setp(ax)
# todo: title always showing up in the last calmap/subplot
# plt.title("Total Daily Steps Heatmap")
plt.savefig("total_daily_steps_heatmap.png")
import matplotlib.pyplot as plt
pd.set_option('display.max_columns', 20)
# KOSPI 데이터 준비
df = pd.read_excel('./data/kospi.xls', parse_dates=['년/월/일'])
print(df.head(), '\n')
df.columns = [
'date', 'price', 'up_down', 'change', 'start', 'high', 'low', 'vol_num',
'vol_amt', 'mkt_cap'
]
df = df.set_index('date', drop=True)
print(df.head(), '\n')
# Calendar Map 표현
plt.figure(figsize=(16, 8))
calmap.calendarplot(
df.change,
monthticks=1,
daylabels='MTWTFSS',
dayticks=[0, 2, 4, 6],
cmap='YlGn',
linewidth=0.05,
fillcolor='grey',
fig_kws=dict(figsize=(14, 6)),
yearlabel_kws=dict(color='black', fontsize=12),
subplot_kws=dict(title='2018 KOSPI Price Trend'),
)
plt.show()
import matplotlib as mpl
import calmap
import pandas as pd
import matplotlib.pyplot as plt
# Import Data
df = pd.read_csv(
"https://raw.githubusercontent.com/selva86/datasets/master/yahoo.csv",
parse_dates=['date'])
df.set_index('date', inplace=True)
# Plot
plt.figure(figsize=(16, 10), dpi=80)
calmap.calendarplot(df['2014']['VIX.Close'],
fig_kws={'figsize': (16, 10)},
yearlabel_kws={
'color': 'black',
'fontsize': 14
},
subplot_kws={'title': 'Yahoo Stock Prices'})
plt.show()
def test_calendarplot(events):
"""
With `calendarplot` we can plot several years in one figure.
"""
fig, axes = calmap.calendarplot(events)
return fig
def test_calendarplot(events):
"""
With `calendarplot` we can plot several years in one figure.
"""
fig, axes = calmap.calendarplot(events)
return fig
def dbplot():
data = pd.read_excel("C:\\Users\\user\\Desktop\\death_criminal.xlsx")
data2 = pd.read_excel("C:\\Users\\user\\Desktop\\death_police.xlsx")
#state = data['State']
state_data = Victims.objects.all()
state_list = []
for i in state_data:
state_list = i.state
state = pd.DataFrame(state_list)
state_list = list(set(state))
state_list_count = {}
state_list_prob = {}
for i in state_list:
state_list_count[i] = 0
for i in range(0, len(data)):
state_data = data['State'][i]
if state_data in state_list:
state_list_count[state_data] += 1
for i, j in state_list_count.items():
state_list_prob[i] = j / len(data)
state_list_count2 = sorted(state_list_count.items(),
reverse=True,
key=lambda item: item[1])
x = []
y = []
for i in range(0, 20):
x.append(state_list_count2[i][0])
y.append(state_list_count2[i][1])
plt.figure(figsize=(10, 5))
plt.bar(x[0:20], y[0:20], color='red')
plt.xlabel('state')
plt.savefig(
'C:/Users/user/Desktop/dbproject/dbwebprograming/rip_floyd/static/img/plot1.png'
)
##날짜 그래프
col1 = 'Date of Incident (month/day/year)'
date_list = list(set(data[col1]))
date_count = {}
for i in range(0, len(data)):
date_data = data[col1][i]
if date_data in date_count:
date_count[date_data] += 1
else:
date_count[date_data] = 1
days = list(date_count.keys())
happens = list(date_count.values())
events = pd.Series(happens, index=days)
calmap.calendarplot(events)
plt.savefig(
'C:/Users/user/Desktop/dbproject/dbwebprograming/rip_floyd/static/img/plot2.png'
)
##인종별
racial_list = list(set(data["Victim's race"]))
racial_list_count = {}
for i in range(0, len(data)):
racial_data = data["Victim's race"][i]
if racial_data in racial_list_count:
racial_list_count[racial_data] += 1
else:
racial_list_count[racial_data] = 1
plt.figure(figsize=(10, 5))
plt.bar(list(racial_list_count.keys())[0:4],
list(racial_list_count.values())[0:4],
color='red')
plt.xlabel('Racial')
plt.savefig(
'C:/Users/user/Desktop/dbproject/dbwebprograming/rip_floyd/static/img/plot3.png'
)
##경찰들 순직사건 주별로
police_list_count = {}
for i in range(0, len(data2)):
data2['state'][i] = data2['state'][i].split(', ')[1]
for i in range(0, len(data2)):
info = data2['state'][i]
if info in police_list_count:
police_list_count[info] += 1
else:
police_list_count[info] = 1
police_list_count2 = sorted(police_list_count.items(),
reverse=True,
key=lambda item: item[1])
x2 = []
y2 = []
for i in range(0, 20):
x2.append(police_list_count2[i][0])
y2.append(police_list_count2[i][1])
plt.figure(figsize=(10, 5))
plt.bar(x2[0:20], y2[0:20], color='red')
plt.xlabel('State')
plt.savefig(
'C:/Users/user/Desktop/dbproject/dbwebprograming/rip_floyd/static/img/plot4.png'
)
##경찰들의 총기순직사건과 범죄자들의 과잉진압 사건 회귀분석
x1_value = [] #state별 범죄사망자
x2_value = [] #state별 경찰사망자
for i in state_list:
x1_value.append(state_list_count.get(i))
x2_value.append(police_list_count.get(i))
reg_x1 = pd.DataFrame(x1_value, index=state_list, columns=['events'])
reg_x2 = pd.DataFrame(x2_value, index=state_list, columns=['events'])
reg_x2 = reg_x2.fillna(0)
reg = LinearRegression()
reg.fit(reg_x1, reg_x2)
r2 = reg.score(reg_x1, reg_x2)
y_pred = reg.predict(reg_x1)
plt.scatter(reg_x1, reg_x2)
plt.plot(reg_x1, y_pred)
plt.savefig(
'C:/Users/user/Desktop/dbproject/dbwebprograming/rip_floyd/static/img/plot5.png'
)
temp.rename(columns={'raining': 'hours_raining'}, inplace=True)
temp['day'] = temp['day'].apply(lambda x: x.to_datetime().date())
rainy_days = rainy_days.merge(temp, left_on='date', right_on='day', how='left')
rainy_days.drop('day', axis=1, inplace=True)
print ("In the year, there were {} rainy days of {} at {}".format(rainy_days['rain'].sum(), len(rainy_days), station) )
print ("It was wet while cycling {} working days of {} at {}".format(wet_cycling['get_wet_cycling'].sum(),
len(wet_cycling),
station))
print ("You get wet cycling {} % of the time!!".format(wet_cycling['get_wet_cycling'].sum()*1.0*100/len(wet_cycling)))
import calmap
temp = rainy_days.copy().set_index(pd.DatetimeIndex(analysis['rainy_days']['date']))
#temp.set_index('date', inplace=True)
fig, ax = calmap.calendarplot(temp['hours_raining'], fig_kws={"figsize":(15,4)})
plt.title("Hours raining")
fig, ax = calmap.calendarplot(temp['total_rain'], fig_kws={"figsize":(15,4)})
plt.title("Total Rainfall Daily")
temp[['get_wet_cycling', 'total_rain', 'hours_raining']].plot()
def analyse_station(data_raw, station):
"""
Function to analyse weather data for a period from one weather station.
Args:
data_raw (pd.DataFrame): Pandas Dataframe made from CSV downloaded from wunderground.com
station (String): Name of station being analysed (for comments)
Returns:
