def plot_koalas(data: Union["ks.DataFrame", "ks.Series"], kind: str, **kwargs):
import plotly
# Koalas specific plots
if kind == "pie":
return plot_pie(data, **kwargs)
if kind == "hist":
return plot_histogram(data, **kwargs)
if kind == "box":
return plot_box(data, **kwargs)
# Other plots.
return plotly.plot(KoalasPlotAccessor.pandas_plot_data_map[kind](data),
kind, **kwargs)
def plot_pandas_on_spark(data: Union["ps.DataFrame", "ps.Series"], kind: str, **kwargs):
import plotly
# pandas-on-Spark specific plots
if kind == "pie":
return plot_pie(data, **kwargs)
if kind == "hist":
return plot_histogram(data, **kwargs)
if kind == "box":
return plot_box(data, **kwargs)
if kind == "kde" or kind == "density":
return plot_kde(data, **kwargs)
# Other plots.
return plotly.plot(PandasOnSparkPlotAccessor.pandas_plot_data_map[kind](data), kind, **kwargs)
else:
dates = [q[0] for q in quotes]
y = [q[1] for q in quotes]
for date in dates:
x.append(datetime.fromordinal(int(date))\
.strftime('%Y-%m-%d')) # Plotly timestamp format
ma = moving_average(y, 10)
# vvv clip first and last points of convolution
mov_avg = go.Scatter( x=x[5:-4], y=ma[5:-4], \
line=dict(width=2,color='red',opacity=0.5), name='Moving average' )
data = [xy_data, mov_avg]
py.iplot(data, filename='apple stock moving average')
first_plot_url = py.plot(data, filename='apple stock moving average', auto_open=False,)
print first_plot_url
tickers = ['AAPL', 'GE', 'IBM', 'KO', 'MSFT', 'PEP']
prices = []
for ticker in tickers:
quotes = quotes_historical_yahoo(ticker, date1, date2)
prices.append( [q[1] for q in quotes] )
df = pd.DataFrame( prices ).transpose()
df.columns = tickers
df.head()
fig = plotly_tools.get_subplots(rows=6, columns=6, print_grid=True, horizontal_spacing= 0.05, vertical_spacing= 0.05)
"""Kernel Density Estimation with Scipy"""
def send():
if request.method == 'POST':
# just output to json file
students = int(request.form['n-students'])
layoutData = list(map(int, request.form['layout-data'].splitlines()))
#layoutData = [int(i) for i in request.form['layout-data']]
femaleRatio = float(request.form['female-ratio'])
maleRatio = float(request.form['male-ratio'])
otherRatio = float(request.form['other-ratio'])
poorRatio = float(request.form['poor-ratio'])
middleClassRatio = float(request.form['middle-class-ratio'])
wealthyRatio = float(request.form['wealthy-ratio'])
nativeRatio = float(request.form['native-ratio'])
eslRatio = float(request.form['esl-ratio'])
results = {
"students":students,
"layoutData":layoutData,
"femaleRatio":femaleRatio,
"maleRatio": maleRatio,
"otherRatio": otherRatio,
"poorRatio": poorRatio,
"middleClassRatio": middleClassRatio,
"wealthyRatio": wealthyRatio,
"nativeRatio": nativeRatio,
"eslRatio": eslRatio
}
f = open('in.json', 'w')
f.write(json.dumps(results))
f.close()
#retrieve input boundaries from user
yearF = request.form['ctl_list_YearFrom']
yearFi = int(yearF)
weekF = request.form['ctl_list_WeekFrom']
weekFi = int(weekF)
yearT = request.form['ctl_list_YearTo']
yearTi = int(yearT)
weekT = request.form['ctl_list_WeekTo']
weekTi = int(weekT)
typeSelect = request.form['selectType']
if typeSelect == "Start End":
df = time_filter_inclusive(yearFi, weekFi, yearTi, weekTi)
dfWS = df
#Week Fixer
if yearFi != yearTi:
i = 0
for index, row in df.iterrows():
if row['Year'] != yearFi:
count = row['Year'] - yearFi
dfWS.iat[i, 1] = row['Week'] + (count * 52)
i += 1
#create graph
A_H1 = Scatter(x = dfWS['Week'], y = dfWS['AH1'], mode = 'markers', name = 'A (H1)')
A_H1N1 = Scatter(x = dfWS['Week'], y = dfWS['AH1N12009'], mode = 'markers', name = 'A (H1N1)')
A_H3 = Scatter(x = dfWS['Week'], y = dfWS['AH3'], mode = 'markers', name = 'A (H3)')
A_H5 = Scatter(x = dfWS['Week'], y = dfWS['AH5'], mode = 'markers', name = 'A (H5)')
A_NoSub = Scatter(x = dfWS['Week'], y = dfWS['ANOTSUBTYPED'], mode = 'markers', name = 'A (No subtype)')
A_Total = Scatter(x = dfWS['Week'], y = dfWS['INF_A'], mode = 'markers', name = 'A Total')
B_Yamagata = Scatter(x = dfWS['Week'], y = dfWS['BYAMAGATA'], mode = 'markers', name = 'B (Yamagata)')
B_Victoria = Scatter(x = dfWS['Week'], y = dfWS['BVICTORIA'], mode = 'markers', name = 'B (Victoria)')
B_NoLineage = Scatter(x = dfWS['Week'], y = dfWS['BNOTDETERMINED'], mode = 'markers', name = 'B (No lineage)')
B_Total = Scatter(x = dfWS['Week'], y = dfWS['INF_B'], mode = 'markers', name = 'B Total')
data = [A_H1, A_H1N1, A_H3, A_H5, A_NoSub, A_Total, B_Yamagata, B_Victoria, B_NoLineage, B_Total]
first_plot_url = py.plot(data, filename='Inclusive Graph', auto_open=False,)
firsttPlotHTML = plotly_tools.get_embed(first_plot_url)
else:
df = time_filter_weekly(yearFi, weekFi, yearTi, weekTi)
dfWS = df
#Week Fixer
if yearFi != yearTi:
i = 0
for index, row in df.iterrows():
if row['Year'] != yearFi:
count = row['Year'] - yearFi
dfWS.iat[i, 1] = row['Week'] + (count * 52)
i += 1
#create graph
A_H1 = Scatter(x = dfWS['Week'], y = dfWS['AH1'], mode = 'markers', name = 'A (H1)')
A_H1N1 = Scatter(x = dfWS['Week'], y = dfWS['AH1N12009'], mode = 'markers', name = 'A (H1N1)')
A_H3 = Scatter(x = dfWS['Week'], y = dfWS['AH3'], mode = 'markers', name = 'A (H3)')
A_H5 = Scatter(x = dfWS['Week'], y = dfWS['AH5'], mode = 'markers', name = 'A (H5)')
A_NoSub = Scatter(x = dfWS['Week'], y = dfWS['ANOTSUBTYPED'], mode = 'markers', name = 'A (No subtype)')
A_Total = Scatter(x = dfWS['Week'], y = dfWS['INF_A'], mode = 'markers', name = 'A Total')
B_Yamagata = Scatter(x = dfWS['Week'], y = dfWS['BYAMAGATA'], mode = 'markers', name = 'B (Yamagata)')
B_Victoria = Scatter(x = dfWS['Week'], y = dfWS['BVICTORIA'], mode = 'markers', name = 'B (Victoria)')
B_NoLineage = Scatter(x = dfWS['Week'], y = dfWS['BNOTDETERMINED'], mode = 'markers', name = 'B (No lineage)')
B_Total = Scatter(x = dfWS['Week'], y = dfWS['INF_B'], mode = 'markers', name = 'B Total')
data = [A_H1, A_H1N1, A_H3, A_H5, A_NoSub, A_Total, B_Yamagata, B_Victoria, B_NoLineage, B_Total]
first_plot_url = py.plot(data, filename='Inclusive Graph', auto_open=False,)
firsttPlotHTML = plotly_tools.get_embed(first_plot_url)
#create html raw data table
dfRaw = df.to_html().replace('<table border="1" class="dataframe">','<table class="table table-striped">') #Table of raw data
dfRaw = dfRaw.replace("<thead>",'<thead class="thead-dark">')
#Run data analysis
df.drop('Year', axis=1, inplace=True)
df.drop('Week', axis=1, inplace=True)
dfSum = df.describe()
#create html summary table
dfSum = dfSum.to_html().replace('<table border="1" class="dataframe">','<table class="table table-striped">') #Table of analyzed data
dfSum = dfSum.replace("<thead>",'<thead class="thead-dark">')
os.remove("/Users/jiabeiluo/Desktop/studentrngdemo/templates/result.html") #clear old results
#HTML code for the results
html_string = '''
<html>
<head>
<!-- Required meta tags -->
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
<!-- Bootstrap CSS -->
<link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css" integrity="sha384-ggOyR0iXCbMQv3Xipma34MD+dH/1fQ784/j6cY/iJTQUOhcWr7x9JvoRxT2MZw1T" crossorigin="anonymous">
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.6/umd/popper.min.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/4.2.1/js/bootstrap.min.js"></script>
<title>Results</title>
<style>
body {
position: relative;
}
</style>
</head>
<body data-spy="scroll" data-target=".navbar" data-offset="50">
<!--NarBar-->
<nav class="navbar navbar-expand-sm bg-dark navbar-dark fixed-top">
<ul class="navbar-nav">
<li class="nav-item">
<a class="nav-link" href="#section1">Data Selection Graph</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#section2">Full Data Selection Results</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#section3">Summary table</a>
</li>
</ul>
</nav>
<div id="section1" class="container-fluid" style="padding-top:70px;padding-bottom:70px">
<div class="container">
<div class="pb2 mt-4 mb-2 border-bottom">
<h2>Data Selection Graph</h2>
</div>
</div>
''' + firsttPlotHTML + '''
</div>
<div id="section2" class="container-fluid" style="padding-top:70px;padding-bottom:70px">
<div class="container">
<div class="pb2 mt-4 mb-2 border-bottom">
<h3>Full Data Selection Results</h3>
</div>
</div>
''' + dfRaw + '''
</div>
<div id="section3" class="container-fluid" style="padding-top:70px;padding-bottom:70px">
<div class="container">
<div class="pb2 mt-4 mb-2 border-bottom">
<h3>Summary table: Data Selection Results</h3>
</div>
</div>
''' + dfSum + '''
</div>
</body>
</html>'''
#create the HTML file
f = open('/Users/jiabeiluo/Desktop/studentrngdemo/templates/result.html','w')
f.write(html_string)
f.close()
#Return results to user
return render_template('result.html')
return render_template('my-form.html')
N = 40
x = np.linspace(0, 1, N)
y = np.random.randn(N)
df = pd.DataFrame({'x': x, 'y': y})
df.head()
data = [
go.Bar(
x=df['x'], # assign x as the dataframe column 'x'
y=df['y']
)
]
# IPython notebook
# py.iplot(data, filename='pandas-bar-chart')
url = py.plot(data, filename='pandas-bar-chart')
# In[197]:
data=db['mc_tweets_to_plot']
data_df =pd.DataFrame(list(data.find({})))
#tweets_to_plot_json = tweets_to_plot_df.to_json(orient='index')
# with open('data.txt', 'w') as outfile:
# json.dump(tweets_to_plot_json , outfile)
data_df.to_csv('twitterdata.csv')
# -*- coding: utf-8 -*-
"""
Created on Thu Aug 1 10:26:23 2019
@author: STEM
"""
import pandas as pd
import plotly
import plotly.offline as plot
import plotly.graph_objs as go
wodf = pd.read_excel("GISdata.xlsx", sheet_name="womenOccupation")
wodf
womenoccupation = go.Bar(x=wodf["occupation"],
y=wodf["women"],
marker={
"color": wodf["women"],
"colorscale": "Jet"
})
plot([womenoccupation])
window = np.ones(int(window_size))/float(window_size)
return np.convolve(interval, window, 'same')
date1 = dt_date( 2014, 1, 1 )
date2 = dt_date( 2014, 12, 12 )
quotes = quotes_historical_yahoo('AAPL', date1, date2)
if len(quotes) == 0:
print "Couldn't connect to yahoo trading database"
else:
dates = [q[0] for q in quotes]
y = [q[1] for q in quotes]
for date in dates:
x.append(datetime.fromordinal(int(date))\
.strftime('%Y-%m-%d')) # Plotly timestamp format
ma = moving_average(y, 10)
#Now graph the data with Plotly. See here for Plotly's line plot
#syntax and here for getting started with the Plotly Python client.
xy_data = Scatter( x=x, y=y, mode='markers', marker=Marker(size=4), name='AAPL' )
# vvv clip first and last points of convolution
mov_avg = Scatter( x=x[5:-4], y=ma[5:-4], \
line=Line(width=2,color='red',opacity=0.5), name='Moving average' )
data = Data([xy_data, mov_avg])
py.iplot(data, filename='apple stock moving average')
#Save the plot URL - we'll use it when generating the report later.
first_plot_url = py.plot(data, filename='apple stock moving average', auto_open=False,)
print first_plot_url
layout = dict(title='Explained variance by different principal components',
yaxis=dict(title='Explained variance in percent'),
annotations=list([
dict(
x=1.16,
y=1.05,
xref='paper',
yref='paper',
text='Explained Variance',
showarrow=False,
)
]))
fig = dict(data=data, layout=layout)
py.plot(fig)
#得到前四个的因子的projection结果
matrix_w = np.hstack(
(eig_pairs[0][1].reshape(13, 1), eig_pairs[1][1].reshape(13, 1),
eig_pairs[2][1].reshape(13, 1), eig_pairs[3][1].reshape(13, 1)))
matrix_w.index = factor_list
'''
0 1 2 3
downside_risk_2 -0.478293 -0.137210 0.384094 0.069760
status_dsr -0.061976 -0.062509 0.211771 0.309597
illiq_2_2 0.249994 0.119395 0.377741 -0.505791
returns_p -0.004464 -0.017830 -0.031858 0.013654
creditRate -0.170669 0.571809 0.004226 -0.081692
default_spread 0.000000 0.000000 0.000000 0.000000
log_trade_value 0.264545 0.140962 0.461324 -0.405704
def plotly_map_r_e_locations():
try:
trace1 = dict(type='scattergeo',
locationmode='USA-states',
lon=event_lon_vals,
lat=event_lat_vals,
text=event_text_vals,
mode='markers',
marker=dict(size=20, symbol='star', color='red'))
trace2 = dict(type='scattergeo',
locationmode='USA-states',
lon=restaurant_lon_vals,
lat=restaurant_lat_vals,
text=restaurant_text_vals,
mode='markers',
marker=dict(size=8, symbol='circle', color='blue'))
data = [trace1, trace2]
min_lat = 10000
max_lat = -10000
min_lon = 10000
max_lon = -10000
lat_vals = event_lat_vals + restaurant_lat_vals
lon_vals = event_lon_vals + restaurant_lon_vals
for str_v in lat_vals:
v = float(str_v)
if v < min_lat:
min_lat = v
if v > max_lat:
max_lat = v
for str_v in lon_vals:
v = float(str_v)
if v < min_lon:
min_lon = v
if v > max_lon:
max_lon = v
center_lat = (max_lat + min_lat) / 2
center_lon = (max_lon + min_lon) / 2
max_range = max(abs(max_lat - min_lat), abs(max_lon - min_lon))
padding = max_range * .10
lat_axis = [min_lat - padding, max_lat + padding]
lon_axis = [min_lon - padding, max_lon + padding]
layout = dict(
title='Local Restaurants and Events<br>(Hover for site names)',
geo=dict(scope='usa',
projection=dict(type='albers usa'),
showland=True,
landcolor="rgb(250, 250, 250)",
subunitcolor="rgb(100, 217, 217)",
countrycolor="rgb(217, 100, 217)",
lataxis={'range': lat_axis},
lonaxis={'range': lon_axis},
center={
'lat': center_lat,
'lon': center_lon
},
countrywidth=3,
subunitwidth=3),
)
fig = dict(data=data, layout=layout)
py.plot(fig, filename='restaurants_and_local_events')
except ValueError:
pass
def do_display_graph(self, graph):
plt.plot(self.graph_data)
else:
dates = [q[0] for q in quotes]
y = [q[1] for q in quotes]
for date in dates:
x.append(datetime.fromordinal(int(date))\
.strftime('%Y-%m-%d')) # Plotly timestamp format
ma = moving_average(y, 10)
# ************************* END importing AAPL INFO
# Graph Creation
xy_data = go.Scatter(x=x,
y=y,
mode='markers',
marker=dict(size=4),
name='AAPL')
# vvv clip first and last points of convolution
mov_avg = go.Scatter( x=x[5:-4], y=ma[5:-4], \
line=dict(width=2,color='red',opacity=0.5), name='Moving average' )
data = [xy_data, mov_avg]
py.iplot(data, filename='apple stock moving average')
# Graph URL
first_plot_url = py.plot(
data,
filename='apple stock moving average',
auto_open=False,
)
print(first_plot_url)
# table_ekf_output
import plotly.offline as py
from plotly.graph_objs import *
# estimations
trace1 = Scatter(x=table_ekf_output['px_est'],
y=table_ekf_output['py_est'],
xaxis='x2',
yaxis='y2',
name='KF- Estimate',
fillcolor='rgb(255,0,0)',
mode='markers')
# Measurements
trace2 = Scatter(x=table_ekf_output['px_meas'],
y=table_ekf_output['py_meas'],
xaxis='x2',
yaxis='y2',
name='Measurements',
fillcolor='rgb(255,255,255)',
mode='markers')
data = [trace1, trace2]
layout = Layout(xaxis2=dict(anchor='x2', title='px'),
yaxis2=dict(anchor='y2', title='py'))
fig = Figure(data=data, layout=layout)
py.plot(fig, filename='EKF')
def plot_data():
DATA_FILE_PATH = 'flightComputer.csv'
DATA_LABELS = {
'time': 0,
'acceleration_x': 1,
'acceleration_y': 2,
'acceleration_z': 3,
'rotation_x': 4,
'rotation_y': 5,
'rotation_z': 6,
'pressure': 7,
'temperature': 8,
'altitude': 9,
'events': 10
}
###LIST FOR TRACES
##NOTE: CHANGE THE COLUMNS ACCORDING TO THE XLS DATA FROM FLIGHT COMP
time = [] #column 1 i.e 0 WILL BE THE X FOR ALL VALUES
acceleration = []
acceleration_x = [] #column 6 in xls, 5 in py
acceleration_y = [] #column 6 in xls, 5 in py
acceleration_z = [] #column 6 in xls, 5 in py
rotation_x = []
rotation_y = []
rotation_z = []
air_pressure = [] #col 51 in xls, 50 in py
temperature = [] #col 50 in xls, 49 in py
velocity = [] #col 5 in xls, 4 in py
altitude = [] #col 2 in xls, 1 in py
inertia = [] #col 23 in xls, 22 in py
thrust = [] #col 29 in xls, 28 in py
data = []
stop_time = 0
with open(DATA_FILE_PATH, newline='') as csvfile:
data_reader = csv.reader(csvfile, delimiter=',', quotechar='|')
for n, row in enumerate(data_reader):
if n == 0:
print(len(row))
for i in range(len(row)):
data.append([])
for i in range(len(row)):
try:
data[i].append(int(row[i]))
except:
data[i].append(float(row[i]))
data = np.array(data)
data = data.astype('float64')
print(data[DATA_LABELS['pressure']])
endIndex = 0
diffs = np.diff(data[DATA_LABELS['time']])
print(diffs)
for p, val in enumerate(diffs):
print(val)
if val > 50.0:
endIndex = p - 1
print("endIndex: {}".format(endIndex))
break
#Data conditioning
for key in DATA_LABELS.keys():
print(key)
if 'acceleration' in key:
print(key)
data[DATA_LABELS[key]] = data[DATA_LABELS[key]] / (2**15) * 12
print(data[DATA_LABELS[key]][1])
if 'temperature' in key:
print(key)
data[DATA_LABELS[key]] = data[DATA_LABELS[key]] / 100
print(data[DATA_LABELS[key]][1])
if 'pressure' in key:
print(key)
data[DATA_LABELS[key]] = data[DATA_LABELS[key]] / 100000
print(data[DATA_LABELS[key]][1])
if 'time' in key:
print(key)
data[DATA_LABELS[key]] = data[DATA_LABELS[key]] / 1000
print(data[DATA_LABELS[key]][1])
# data[DATA_LABELS[key]] = data[DATA_LABELS[key]][:endIndex]
##Accleration trace
trace1 = {
'x': data[DATA_LABELS['time']]
[:endIndex], #put the x values here, they are same for all i.e time
'y': data[DATA_LABELS['acceleration_x']]
[:endIndex], #put the y values i want, i.e this is acceleration column
'mode': 'lines', #want a line curve
'name':
'ACCELERATION X (m/s^2)', #name of the trace i want i.e name of y
'type': 'scatter', #want to create scatter plots of these values
'xaxis': 'x',
'yaxis': 'y'
}
trace2 = {
'x': data[DATA_LABELS['time']][:endIndex],
'y': data[DATA_LABELS['acceleration_y']][:endIndex],
'mode': 'lines',
'name': 'ACCELERATION Y (m/s)',
'type': 'scatter',
'xaxis': 'x',
'yaxis': 'y'
}
trace3 = {
'x': data[DATA_LABELS['time']][:endIndex],
'y': data[DATA_LABELS['acceleration_z']][:endIndex],
'mode': 'lines',
'name': 'ACCELERATION Z',
'type': 'scatter',
'xaxis': 'x',
'yaxis': 'y'
}
trace4 = {
'x': data[DATA_LABELS['time']][:endIndex],
'y': data[DATA_LABELS['altitude']][:endIndex],
'mode': 'lines',
'name': 'Altitude (m)',
'type': 'scatter',
'xaxis': 'x',
'yaxis': 'y'
}
trace5 = {
'x': data[DATA_LABELS['time']][:endIndex],
'y': data[DATA_LABELS['events']][:endIndex],
'mode': 'lines',
'name': 'Events',
'type': 'scatter',
'xaxis': 'x',
'yaxis': 'y'
}
trace6 = {
'x': data[DATA_LABELS['time']][:endIndex],
'y': data[DATA_LABELS['pressure']][:endIndex],
'mode': 'lines',
'name': 'AIR PRESSURE (kPa)',
'type': 'scatter',
'xaxis': 'x',
'yaxis': 'y'
}
trace7 = {
'x': data[DATA_LABELS['time']][:endIndex],
'y': data[DATA_LABELS['temperature']][:endIndex],
'mode': 'lines',
'name': 'TEMPERATURE (C)',
'type': 'scatter',
'xaxis': 'x',
'yaxis': 'y'
}
#do same for all the components i want
data = [trace1, trace2, trace3, trace4, trace5, trace6,
trace7] #put the name of all the traces
#
layout = {
"autosize": True,
"dragmode": "pan",
"showlegend": True,
"title": {
# "x": 0.48,
"font": {
"size": 20
},
"text": "FLIGHT DATA ANALYSIS (UMSATS ROCKETRY)"
},
"xaxis": {
"autorange": True,
"range": [0, 180.91],
"rangeslider": {
"autorange": True,
"range": [0, 180.91],
"visible": False
},
"title": {
"text": "Time (s)"
},
"type": "linear"
},
"yaxis": {
"autorange": True,
"range": [-173.70122222222219, 3205.563222222222],
"showspikes": False,
"title": {
"text": "Flight data"
},
"type": "linear"
}
}
fig = dict(data=data, layout=layout)
ply.plot(fig, filename='app/templates/Plot.html', auto_open=False)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri May 11 17:34:30 2018
@author: batman
"""
print_imports()
import plotly as py
py.plotly.plotly.tools.set_credentials_file(username='******', api_key='1hy2cho61mYO4ly5R9Za')
import plotly.graph_objs as pg
trace0 = pg.Scatter(
x=[1, 2, 3, 4],
y=[10, 15, 13, 17]
)
trace1 = pg.Scatter(
x=[1, 2, 3, 4],
y=[16, 5, 11, 9]
)
data = pg.Data([trace0, trace1])
py.plot(data, filename = 'basic-line')
py.offline.plot({
"data": [pg.Scatter(x=[1, 2, 3, 4], y=[4, 3, 2, 1])],
"layout": pg.Layout(title="hello world")
})
def plotClusters(data):
'''
Use the plotly API to plot data from clusters.
Gets a plot URL from plotly and then uses subprocess to 'open' that URL
from the command line. This should open your default web browser.
'''
# List of symbols each cluster will be displayed using
symbols = ['circle', 'cross', 'triangle-up', 'square']
# Convert data into plotly format.
traceList = []
for i, c in enumerate(data):
data = []
for p in c.points:
data.append(p.coords)
# Data
trace = {}
trace['x'], trace['y'] = zip(*data)
trace['marker'] = {}
trace['marker']['symbol'] = symbols[i]
trace['name'] = "Cluster " + str(i)
traceList.append(trace)
# Centroid (A trace of length 1)
centroid = {}
centroid['x'] = [c.centroid.coords[0]]
centroid['y'] = [c.centroid.coords[1]]
centroid['marker'] = {}
centroid['marker']['symbol'] = symbols[i]
centroid['marker']['color'] = 'rgb(200,10,10)'
centroid['name'] = "Centroid " + str(i)
traceList.append(centroid)
# Log in to plotly
#py = plotly(username=PLOTLY_USERNAME, key=PLOTLY_KEY)
# Style the chart
''' datastyle = {'mode': 'markers',
'type': 'scatter',
'marker': {'line': {'width': 0},
'size': 12,
'opacity': 0.6,
'color': 'rgb(74, 134, 232)'}}
resp = py.plot(*traceList, style=datastyle)
# Display that plot in a browser
cmd = "open " + resp['url']
subprocess.call(cmd, shell=True)'''
# Style the chart
layout = dict(
title='Plot',
xaxis=dict(title='X axis'),
yaxis=dict(title='Y axis'),
plot_bgcolor='lightblue',
)
fig = dict(data=traceList, layout=layout)
py.offline.iplot(fig)
resp = py.plot(*traceList, style=layout)
# Display that plot in a browser
cmd = "open " + resp['url']
subprocess.call(cmd, shell=True)
x=table_ekf_output['px_gt'],
y=table_ekf_output['py_gt'],
xaxis='x2',
yaxis='y2',
name='Ground Truth',
mode='markers'
)
data = [trace1, trace2, trace3]
layout = Layout(
xaxis2=dict(
anchor='x2',
title='px'
),
yaxis2=dict(
anchor='y2',
title='py'
)
)
fig = Figure(data=data, layout=layout)
py.plot(fig, filename='EKF')
x=table_ekf_output['px_est'],
y=table_ekf_output['py_est'],
py.plot(x,y,color='blue',linestyle='solid',marker='o')
plt.hist(cell['Age'], color='green', edgecolor='black')
plt.xlabel('Age')
plt.ylabel('Smoke') #correct the label 'smoke' isnt right
plt.title('Figure 7: for Age Levels')
plt.show()
#Boxplot
plt.boxplot(cell['Calories'])
plt.xlabel('Number of Calories')
plt.title('Figure 8: Boxplot of Caloric Intake')
plt.show()
plt.boxplot(cell['Fat'])
plt.xlabel('Fat Levels')
plt.title('Figure 9: Boxplot of Fat Levels')
plt.show()
plt.plot(cell['Age'])
plt.xlabel('Age of Smokers')
plt.title('Figure 10: Boxplot of Fat Levels')
plt.show()
#Tables Rel. Freq.
print(cell['Calories'].value_counts())
a = pd.crosstable(cell.Calories, columns='Calories')
print(s)
s_rel = a / a.sum()
print(s_rel)
return '重要保持客户'
elif x == '低低高':
return '重要挽留客户'
elif x == '高高低':
return '一般价值客户'
elif x == '高低低':
return '一般发展客户'
elif x == '低高低':
return '一般保持客户'
else:
return '一般挽留客户'
rfm['用户等级'] = rfm['value'].apply(trans_value)
rfm['用户等级'].value_counts()
trade_basic = [
go.Bar(x=rfm['用户等级'].value_counts().index,
y=rfm['用户等级'].value_counts().values,
marker=dict(color='orange'),
opacity=0.50)
]
layout = go.Layout(title='用户等级情况', xaxis=dict(title='用户重要度'))
figure_basic = go.Figure(data=trade_basic, layout=layout)
py.plot(figure_basic)
# trace = [go.Pie(labels= rfm['用户等级'].value_counts().index, values=rfm['用户等级'].value_counts().values,textfont=dict(size=12,color='white'))]
# layout2 = go.Layout(title='用户等级比例')
# figure_basic2 = go.Figure(data= trace,layout=layout2)
# py.plot(figure_basic2)
#结论和建议
paso = paso + 1
else:
paso = paso + np.random.randint(1,7)
if np.random.rand() <= 0.001:
paso = 0
caminata_aleatoria.append(paso) #Agregar el numero que se creo
Todas.append(caminata_aleatoria)
#Al terminar de correr obtenemos una caminata aleatoria el cual nombraremos Todas
#Graficaremos los resultados obtenidos.
np_Todas = np.array(Todas) #Convertimos en array el objeto Todas
plt.plot(np_Todas)
plt.show()
plt.clf()
np_Todas_transpuesta = np.transpose(np_Todas)
plt.plot(np_Todas_transpuesta)
plt.show()
Final = np_Todas[-1,:]
plt.hist(Final)
plt.show()
np.mean(Final[Final > 30]) #Calculo de la media de datos que se ecuentran en la cola de datos aleatorios con un valor mayor a 30
################################
#Definicion simple de funciones#
