def kamervragen_reply_time_per_year(years, kamervraag_durations):
fig = ff.create_distplot(
kamervraag_durations,
years,
# colors=colors,
bin_size=1,
show_curve=True,
show_hist=False,
show_rug=False
)
xaxis = XAxis(range=[0, 60])
fig['layout'].update(xaxis=xaxis)
# fig['layout'].update(title="Kamervraag Antwoordtijd per Ministerie tijdens Rutte-II (KDE probability distributie)")
fig['layout'].update(xaxis=dict(title='Antwoordtijd [dagen]'))
# fig['layout'].update(yaxis=dict(title=''))
fig['layout'].update(height=700)
fig['layout'].update(margin=Margin(t=20))
legend = dict(
# x=0.01,
# y=1,
bordercolor='#E2E2E2',
bgcolor='#FFFFFF',
borderwidth=2
)
fig['layout'].update(legend=legend)
return Plot.create_plot_html_default(figure_or_data=fig)
def plot_1d_coupling_profile(couplings_per_bin, plot_dir, ab):
group_labels = [ str(bindict['lower']) + "Å < ΔCβ < " + str(bindict['upper']) + "Å" for binname, bindict in sorted(couplings_per_bin.iteritems(), reverse=True)]
hist_data = [bindict['couplings'] for binname, bindict in sorted(couplings_per_bin.iteritems(), reverse=True)]
nr_datapoints = int(np.round(np.mean([len(x) for x in hist_data]), decimals=-2))
# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, show_hist=False, show_rug=False)
for trace in fig['data']:
trace['line']['width'] = 2
fig['layout']['font'] = dict(size = 16)
fig['layout']['xaxis']['title'] = "couplings w_ij("+ab+")"
fig['layout']['xaxis']['range'] = [-1,1]
fig['layout']['yaxis']['title'] = "Distribution of couplings for " + ab
fig['layout']['margin']['t'] = 10
plot_name = plot_dir + "/1d_coupling_profile_"+ ab + "_avgdatapoints"+str(nr_datapoints)+".html"
plotly_plot(fig, filename=plot_name, auto_open=False)
def plot_density(protein, bqij_data, plot_dir):
group_labels = [key for key in sorted(bqij_data.keys()) if key != "L"]
L = bqij_data['L']
hist_data = []
data=[]
for group in group_labels:
bqij_file = bqij_data[group]
Nij, qij = io.read_qij(bqij_file, bqij_data['L'])
data_group = qij[np.triu_indices(n=L, k=1)].flatten()
hist_data.append(data_group)
data.append(
go.Histogram(
x=data_group,
histnorm='probability',
name=group,
xbins=dict(
start=-0.1,
end=1,
size=0.005
),
opacity=0.75
)
)
# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, show_hist=False, show_rug=False)
fig['layout']['font'] = dict(size = 18)
fig['layout']['xaxis']['title'] = "q_ijab"
plot_file = plot_dir + "/" + protein + "_distribution_qijab" + ".html"
plotly_plot(fig, filename=plot_file, auto_open=False)
#create histogram
plot_file = plot_dir + "/" + protein + "_histogram_qijab" + ".html"
layout = go.Layout(
barmode='overlay',
xaxis=dict(
title="q_ijab",
exponentformat="e",
showexponent='All'
),
yaxis=dict(
exponentformat="e",
showexponent='All'
),
font=dict(size = 18)
)
fig = go.Figure(data=data, layout=layout)
plotly_plot(fig, filename=plot_file, auto_open=False)
def set_display_children(slct_row, data, columns):
dt_tmp = pd.DataFrame(data, columns=[c['id'] for c in columns])
idx = dt_tmp.iloc[list(slct_row)]['idx']
fig = ff.create_distplot([dt_ni[i] for i in idx], [str(i) for i in idx], bin_size=.5, show_rug=False,
show_curve=False)
fig.layout.update(title='Histogram of Mean Return')
fig.layout.xaxis.update({'title': 'Mean Return (In Dollar$) '})
return dcc.Graph(
figure=fig,
id='my-graph_rec'
)
def plot_distance_distribution(distances_ab, ab, distance_definition, log, plot_dir):
group_labels = ["sequence separation " + str(seq_sep) for seq_sep, values in sorted(distances_ab.iteritems())]
hist_data = [np.array(values[ab])[~np.isnan(values[ab])] for seq_sep, values in sorted(distances_ab.iteritems())]
if log:
hist_data = [ np.log(np.array(values[ab]))[~np.isnan(values[ab])] for seq_sep, values in sorted(distances_ab.iteritems())]
# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, show_hist=False, show_rug=False)
for trace in fig['data']:
trace['line']['width'] = 2
if log:
trace['text'] = ['Cb distance: ' + str(x) for x in np.exp(trace['x'])]
else:
trace['text'] = ['Cb distance: ' + str(x) for x in trace['x']]
trace['hoverinfo'] = "text"
residues = ab[0] + " and " + ab[2]
if ab == 'all':
residues = "residue pair"
fig['layout']['font'] = dict(size = 16)
fig['layout']['xaxis']['title'] = distance_definition + " distance between " + residues
fig['layout']['xaxis']['showspikes'] = True
fig['layout']['yaxis']['title'] = "Distribution of " + residues + " distances ("+distance_definition+")"
fig['layout']['yaxis']['showspikes'] = True
fig['layout']['xaxis']['range'] = [3,100]
fig['layout']['xaxis']['tickangle'] = 0
fig['layout']['margin']['t'] = 10
plot_file = plot_dir + "/" + distance_definition + "_distribution_" + ab + "_data" + str(int(np.mean([len(h) for h in hist_data])))+".html"
if log:
fig['layout']['xaxis']['tickmode'] = "array"
fig['layout']['xaxis']['ticktext'] = [3,4,5,6,8,10,12,15,20,30,40,50,70,80]
fig['layout']['xaxis']['tickvals'] = np.log(fig['layout']['xaxis']['ticktext'])
fig['layout']['xaxis']['range'] = np.log([3,100])
plot_file = plot_file.replace(".html","_log.html")
plotly_plot(fig, filename=plot_file, auto_open=False)
def plot_density(samples,PI = []):
data = []
hist_data = [samples]
group_labels = ['group1']
KDE = ff.create_distplot(hist_data, group_labels,show_hist=False,show_rug=False)
layout = go.Layout(
autosize=False,
width=500,
height=500,
margin=go.Margin(
l=50,
r=50,
b=100,
t=100,
pad=4
),
xaxis=dict(title='x'),
yaxis=dict(title='PDF(x)')
)
trace1 = go.Scatter(
y= KDE['data'][0]['y'],
x = KDE['data'][0]['x'],
mode = 'lines',line=dict(width=2),name='PDF',
fill= None)
data.append(trace1)
if not PI:
return go.Figure(data=data, layout=layout)
### plot the PI interval
y = KDE['data'][0]['y']
x = KDE['data'][0]['x']
df=pd.DataFrame(y,x,columns=['Y'])
df.index.name = 'X'
df=df.loc[(df.index> PI[0]) & (df.index < PI[1]),:]
trace2 = go.Scatter(y= df.Y.values,x = df.index,mode = 'line',fill= 'tozeroy',
line=dict(width=0.0),name='PI' + ' [' + str(PI[0]) + ',' + str(PI[1]) + ']')
data.append(trace2)
return go.Figure(data=data, layout=layout)
def plot_1d_coupling_profile(couplings_per_pair, lower_cb_distance, upper_cb_distance, plot_file ):
group_labels = [key + "("+str(len(couplings_per_pair[key]))+")" for key in couplings_per_pair.keys()]
hist_data = couplings_per_pair.values()
# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, show_hist=False, show_rug=False)
for trace in fig['data']:
trace['line']['width'] = 2
fig['layout']['font'] = dict(size = 16)
fig['layout']['xaxis']['title'] = "couplings w_ijab for residue pairs ij at {0}Å < ΔCβ < {1}Å".format(lower_cb_distance, upper_cb_distance)
fig['layout']['xaxis']['range'] = [-1,1]
fig['layout']['yaxis']['title'] = "Distribution of couplings "
fig['layout']['margin']['t'] = 10
plotly_plot(fig, filename=plot_file, auto_open=False)
import plotly.figure_factory as ff
import plotly.graph_objects as go
import statistics
import random
import pandas as pd
import csv
df = pd.read_csv("data.csv")
data = df["average"].tolist()
fig = ff.create_distplot([data],["average"],show_hist = False)
fig.show()
mean = statistics.mean(data)
std_deviation = statistics.stdev(data)
print("mean of samples: ", mean)
print("standard deviation of sample",std_deviation)
def create_distplot(*args, **kwargs):
FigureFactory._deprecated('create_distplot')
from plotly.figure_factory import create_distplot
return create_distplot(*args, **kwargs)
import plotly.figure_factory as pf
import statistics
import random
import pandas as pd
import csv
df = pd.read_csv('medium_data.csv')
data = df['reading_time'].tolist()
fig = pf.create_distplot([data], ["Reading Time"], show_hist=False)
fig.show()
print("Population Mean ", statistics.mean(data))
def randomSetOfMeans(counter):
dataSet = []
for i in range(0, counter):
randomIndex = random.randint(0, len(data))
value = data[randomIndex]
dataSet.append(value)
mean = statistics.mean(dataSet)
return mean
def showFig(meanList):
df = meanList
fig = pf.create_distplot([df], ["Reading Time"], show_hist=False)
fig.show()
def show_fig(mean_list):
df = mean_list
mean = statistics.mean(df)
fig = ff.create_distplot([df], ["average"], show_hist=False)
fig.add_trace(go.Scatter(x=[mean, mean], y=[0, 1], mode="lines", name="MEAN"))
fig.show()
dev = st.stdev(arr)
return dev
def percent(arr, mean, std):
m1 = int(round(mean - std * 2, 0))
m2 = int(round(mean + std * 2, 0))
count = 0
for i in arr:
if int(round(i)) in range(m1, m2):
count += 1
percent = (count / len(arr)) * 100
return percent
mean = Mean(arr)
median = Median(arr)
mode = Mode(arr)
stdev = standardDev(arr)
per = percent(arr, mean, stdev)
print(f"Mean is {mean}")
print(f"Median is {median}")
print(f"Mode is {mode}")
print(f"Standard Deviation is {stdev}")
print(f"Percentage is {per}")
fig = ff.create_distplot([arr], ["Data"], show_hist=False)
fig.show()
from sklearn.model_selection import train_test_split
import xgboost as xgb
import plotly.figure_factory as ff
from functions import *
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
dt = pd.read_csv('all_data.csv')
dt = dt[[
'(%)lymphocyte', 'High sensitivity C-reactive protein',
'Lactate dehydrogenase', 'outcome'
]]
fig = ff.create_distplot([dt['(%)lymphocyte'].dropna().to_numpy()],
['lymphocytes'])
fig2 = ff.create_distplot(
[dt['High sensitivity C-reactive protein'].dropna().to_numpy()],
['hs-CRP'])
fig3 = ff.create_distplot([dt['Lactate dehydrogenase'].dropna().to_numpy()],
['LDH'])
app.layout = html.Div(children=[
html.H1(children='Interactive survival prediction model'),
html.Div(children=[
html.Label("Choose your patient's nationality:"),
dcc.RadioItems(
id='nation',
options=[{
'label': i,
'value': i
# you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import streamlit as st import numpy as np from plotly import figure_factory # Add histogram data x1 = np.random.randn(200) - 2 x2 = np.random.randn(200) x3 = np.random.randn(200) + 2 # Group data together hist_data = [x1, x2, x3] group_labels = ["Group 1", "Group 2", "Group 3"] bin_size = [0.1, 0.25, 0.5] # Create distribution plot with custom bin_size chart = figure_factory.create_distplot(hist_data, group_labels, bin_size) # Plot! st.plotly_chart(chart)
def _distplot(df):
data = df.T.values
labels = [str(i) for i in df.columns]
result = ff.create_distplot(data, labels)
return result["data"], result["layout"]
def show_fig(mean_list):
df = mean_list
fig = ff.create_distplot([df], ["average"], show_hist=False)
fig.show()
#Finding patterns between the sum of dice results
import random
import plotly.figure_factory as ff
count = []
diceResult = []
for i in range(0, 100):
dice1 = random.randint(1, 6)
dice2 = random.randint(1, 6)
diceResult.append(dice1 + dice2)
count.append(i)
fig = ff.create_distplot([diceResult], ["result"])
fig.show()
def main():
st.button("Re-run")
#set up layout
st.title("Welcome to the pag3")
st.markdown("Coming soon ... Sign up [here]() to get notified.")
#### MAP OPEN-STREET MAP #####
df = pd.DataFrame(np.random.randn(1000, 2) / [50, 50] + [37.76, -122.4],
columns=['lat', 'lon'])
st.map(df)
# #### GRAPH-VISUAL #####
import graphviz as graphviz
# Create a graphlib graph object
graph = graphviz.Digraph()
graph.edge('run', 'intr')
graph.edge('intr', 'runbl')
graph.edge('runbl', 'run')
graph.edge('run', 'kernel')
graph.edge('kernel', 'zombie')
graph.edge('kernel', 'sleep')
graph.edge('kernel', 'runmem')
graph.edge('sleep', 'swap')
graph.edge('swap', 'runswap')
graph.edge('runswap', 'new')
graph.edge('runswap', 'runmem')
graph.edge('new', 'runmem')
graph.edge('sleep', 'runmem')
st.graphviz_chart(graph)
# ### SINGLE-TABLE ####
st.subheader('DATAFRAME')
df = pd.DataFrame(np.random.randn(50, 20),
columns=('col %d' % i for i in range(20)))
st.dataframe(df) # Same as st.write(df)
### SINGLE-TABLE - yellowMAX ####
st.subheader('DATAFRAME WITH MAX UNDERLIANED')
df = pd.DataFrame(np.random.randn(10, 20),
columns=('col %d' % i for i in range(20)))
st.dataframe(df.style.highlight_max(axis=0))
### STATIC TABLE ####
#Display a static table.
''' This differs from st.dataframe in that the table in this case is static:
its entire contents are laid out directly on the page.'''
st.subheader('TABLE')
df = pd.DataFrame(np.random.randn(10, 5),
columns=('col %d' % i for i in range(5)))
st.table(df)
### LINE CHART ####
st.subheader('LINE CHART')
chart_data = pd.DataFrame(np.random.randn(20, 3), columns=['a', 'b', 'c'])
st.line_chart(chart_data)
### LINE CHART AREA####
st.subheader('LINE CHART AREA')
chart_data = pd.DataFrame(np.random.randn(20, 3), columns=['a', 'b', 'c'])
st.area_chart(chart_data)
#### BAR-CHART #####
st.subheader('BAR CHART')
chart_data = pd.DataFrame(np.random.randn(50, 3), columns=["a", "b", "c"])
st.bar_chart(chart_data)
#### HISTOGRAM-MATPLOTLIB #####
import matplotlib.pyplot as plt
st.subheader('HISTOGRAM MATPLOTLIB')
arr = np.random.normal(1, 1, size=100)
fig, ax = plt.subplots()
ax.hist(arr, bins=20)
st.pyplot(fig)
#### scatter-ALTAIR #####
st.subheader('SCATTER ALTAIR')
import altair as alt
df = pd.DataFrame(np.random.randn(200, 3), columns=['a', 'b', 'c'])
c = alt.Chart(df).mark_circle().encode(x='a',
y='b',
size='c',
color='c',
tooltip=['a', 'b', 'c'])
st.altair_chart(c, use_container_width=True)
#### PLOTLY #########
st.subheader('PLOTLY DIAGRAM')
import plotly.figure_factory as ff
# Add histogram data
x1 = np.random.randn(200) - 2
x2 = np.random.randn(200)
x3 = np.random.randn(200) + 2
# Group data together
hist_data = [x1, x2, x3]
group_labels = ['Group 1', 'Group 2', 'Group 3']
# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, bin_size=[.1, .25, .5])
# Plot!
st.plotly_chart(fig, use_container_width=True)
#### BOKEH #########
st.subheader('BOKEH')
from bokeh.plotting import figure
x = [1, 2, 3, 4, 5]
y = [6, 7, 2, 4, 5]
p = figure(title='simple line example', x_axis_label='x', y_axis_label='y')
p.line(x, y, line_width=2)
st.bokeh_chart(p, use_container_width=True)
#### Plotly 2 ################
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.graph_objects as go
from numpy import random
pts = 50
x1 = np.arange(pts)
y1 = np.random.rand(pts)
y2 = np.random.rand(pts)
y3 = (x1 / pts)**2
fig = make_subplots(rows=1, cols=2)
fig.add_trace(go.Scatter(x=x1, y=y1, mode='markers', name='markers'),
row=1,
col=1)
fig.add_trace(go.Scatter(x=x1, y=y2, mode='markers', name='markers2'),
row=1,
col=2)
fig.add_trace(go.Scatter(x=x1, y=y3, mode='lines', name='lines'),
row=1,
col=2)
fig.update_layout(height=300,
width=800,
title_text="Side By Side Subplots")
st.plotly_chart(fig)
#### exagonbar-3d ###########################################
st.subheader('exagon bar-3d')
import pydeck as pdk
df = pd.DataFrame(np.random.randn(1000, 2) / [50, 50] + [37.76, -122.4],
columns=['lat', 'lon'])
st.pydeck_chart(
pdk.Deck(
map_style='mapbox://styles/mapbox/light-v9',
initial_view_state=pdk.ViewState(
latitude=37.76,
longitude=-122.4,
zoom=11,
pitch=50,
),
layers=[
pdk.Layer(
'HexagonLayer',
data=df,
get_position='[lon, lat]',
radius=200,
elevation_scale=4,
elevation_range=[0, 1000],
pickable=True,
extruded=True,
),
pdk.Layer(
'ScatterplotLayer',
data=df,
get_position='[lon, lat]',
get_color='[200, 30, 0, 160]',
get_radius=200,
),
],
))
#### exagonbar-3d ACCIDENT ###########################################
UK_ACCIDENTS_DATA = (
'https://raw.githubusercontent.com/uber-common/'
'deck.gl-data/master/examples/3d-heatmap/heatmap-data.csv')
# Define a layer to display on a map
layer = pdk.Layer('HexagonLayer',
UK_ACCIDENTS_DATA,
get_position=['lng', 'lat'],
auto_highlight=True,
elevation_scale=50,
pickable=True,
elevation_range=[0, 3000],
extruded=True,
coverage=1)
# Set the viewport location
view_state = pdk.ViewState(longitude=-1.415,
latitude=52.2323,
zoom=6,
min_zoom=5,
max_zoom=15,
pitch=40.5,
bearing=-27.36)
# Render
st.pydeck_chart(pdk.Deck(layers=[layer], initial_view_state=view_state))
#### one-image ###########################################
st.subheader('one-image from URL')
from PIL import Image
#image = Image.open('images/cat.jpg')
image = 'https://static.streamlit.io/examples/cat.jpg'
st.image(image, use_column_width=True)
#### more-images###########################################
st.subheader('more-images')
col1, col2, col3 = st.beta_columns(3)
with col1:
st.header("A cat")
st.image("https://static.streamlit.io/examples/cat.jpg",
use_column_width=True)
with col2:
st.header("A dog")
st.image("https://static.streamlit.io/examples/dog.jpg",
use_column_width=True)
with col3:
st.header("An owl")
st.image("https://static.streamlit.io/examples/owl.jpg",
use_column_width=True)
#### display -code ###########################################
st.subheader('display code')
with st.echo():
st.write('This code will be printed')
show_footer()
import plotly.figure_factory as ff
import pandas as pd
import csv
df = pd.read_csv("data.csv")
fig = ff.create_distplot([df["Avg Rating"].tolist()], ["Avg Rating"])
fig.show()
import statistics
import random
import plotly.graph_objects as go
reader = pd.read_csv("temp.csv")
data = reader["temp"].tolist()
mean = statistics.mean(data)
std = statistics.stdev(data)
print(mean)
print(std)
data1 = []
for i in range(0, 1000):
index = random.randint(0, len(data))
value = data[index]
data1.append(value)
print(data1)
mean1 = statistics.mean(data1)
std1 = statistics.stdev(data1)
print("mean of sample data = ", mean1)
print("std of smaple data = ", std1)
graph = ff.create_distplot([data1], ["temp"], show_hist=False)
graph.add_trace(
go.Scatter(x=[mean, mean1], y=[0, 1], mode="lines", name="mean"))
graph.show()
import statistics
import plotly.figure_factory as ff
df = pd.read_csv("height-weight.csv")
heightlist = df["Height(Inches)"].to_list()
weightlist = df["Weight(Pounds)"].to_list()
heightmean = statistics.mean(heightlist)
weightmean = statistics.mean(weightlist)
heightmode = statistics.mode(heightlist)
weightmode = statistics.mode(weightlist)
heightmedian = statistics.median(heightlist)
weightmedian = statistics.median(weightlist)
print("mean,median,mode of height is: {} ,{} ,{} respectively".format(heightmean,heightmedian,heightmode) )
print("mean,median,mode of weight is: {} ,{} ,{} respectively".format(weightmean,weightmedian,weightmode) )
fig = ff.create_distplot([heightlist],["result"],show_hist = False)
fig1 = ff.create_distplot([weightlist],["result"],show_hist = False)
fig.show()
fig1.show()
stdht = statistics.stdev(heightlist)
stdwt = statistics.stdev(weightlist)
print("the standard deviation of height and weight is: {},{} respectively".format(stdht,stdwt))
height1ststart,height1stend = heightmean - stdht,heightmean + stdht
height2ststart,height2stend = heightmean - (2*stdht),heightmean + (2*stdht)
height3ststart,height3stend = heightmean - (3*stdht),heightmean + (3*stdht)
weight1ststart,weight1stend = weightmean - stdwt,weightmean + stdwt
weight2ststart,weight2stend = weightmean - (2*stdwt),weightmean + (2*stdwt)
def update_graph(chart):
trace1 = []
for age in ['0-17', '18-25', '26-35', '36-45', '46-50', '51-55', '55+']:
trace1.append(go.Box(
y=df[df["Age Group"] == age]['Purchase'],
name=age))
layout1 = go.Layout(
title="Purchase vs Age group",
xaxis={"title": "Age Group"},
yaxis={"title": "Sales ($)"},
colorway=['#b2182b', '#ef8a62', '#fddbc7', '#E7E7E7', '#d1e5f0', '#67a9cf', '#2166ac']
)
df_bar = df.groupby(["Occupation"])['Purchase'].sum().reset_index()
trace2 = [go.Bar(
x=df_bar["Occupation"],
y=df_bar["Purchase"],
marker={'color': '#ef8a62', 'line': {'color': "#b2182b", 'width': 0.5}},
opacity=0.6,
error_y={'type': 'percent', 'value': 10}
)]
layout2 = go.Layout(
title="Purchase vs Occupation Types",
xaxis={"title": "Occupation Category (20 Types)"},
yaxis={"title": "Sales ($)"}
)
trace3 = []
for product in ['Product 1', 'Product 2', 'Product 3']:
trace3.append(go.Histogram(
x=df[product],
name=product,
xbins={
"size": 3},
opacity=0.8
))
layout3 = go.Layout(
title="Product Category Distribution",
xaxis={"title": "Products"},
yaxis={"title": "Frequency"},
barmode='overlay',
colorway=['#e9a3c9', '#ffffbf', '#a1d76a']
)
trace4 = [go.Histogram2d(x=df["Age Group"].sort_values(),
y=df['Purchase'],
histnorm='probability',
autobinx=False,
xbins={
"size": 1},
autobiny=False,
ybins={
"size": 1000},
colorscale=[[0, 'rgb(12,51,131)'],
[0.25, 'rgb(10,136,186)'],
[0.5, 'rgb(242,211,56)'],
[0.75, 'rgb(242,143,56)'],
[1, 'rgb(217,30,30)']]
)]
layout4 = go.Layout(
title="Sales vs Age Group distribution",
xaxis={"title": "Age Group"},
yaxis={"title": "Sales ($)"}
)
x1 = df[df["City"] == "A"]["Purchase"]
x2 = df[df["City"] == "B"]["Purchase"]
x3 = df[df["City"] == "C"]["Purchase"]
hist_data = [x1, x2, x3]
group_labels = ["City A", "City B", "City C"]
figure5 = ff.create_distplot(hist_data, group_labels, bin_size=1000, colors=['#a6cee3', '#1f78b4', '#b2df8a'])
figure5['layout'].update(title='Sales Distribution Over Cities',
# xaxis={"title":"Bins"},
yaxis={"title": " Probability Density of Sales"})
trace6 = [
{"type": 'violin',
"x": df[df['Gender'] == 'M']["Resident of the current city"],
"y": df[df['Gender'] == 'M']["Purchase"],
"legendgroup": 'M',
"scalegroup": 'M',
"name": 'Male',
"box": {
"visible": True
},
"meanline": {
"visible": True
},
"line": {
"color": '#C1EC00'
}},
{"type": 'violin',
"x": df[df['Gender'] == 'F']["Resident of the current city"],
"y": df[df['Gender'] == 'F']["Purchase"],
"legendgroup": 'F',
"scalegroup": 'F',
"name": 'Female',
"box": {
"visible": True
},
"meanline": {
"visible": True
},
"line": {
"color": '#EC7899'
}}
]
layout6 = go.Layout(
title="Sales Distribution Over Duration of Stay",
xaxis={"title": " Duration of Stay (years)"},
yaxis={"title": "Sales ($)"},
violinmode="group")
if chart == "Box Plot":
return {
"data": trace1,
"layout": layout1
}
elif chart == "Error Bar":
return {
"data": trace2,
"layout": layout2
}
elif chart == "Histogram":
return {
"data": trace3,
"layout": layout3
}
elif chart == "2D Histogram":
return {
"data": trace4,
"layout": layout4
}
elif chart == "Distplot":
return figure5
else:
return {
"data": trace6,
"layout": layout6
}
import plotly.figure_factory as ff
import plotly.graph_objects as go
import statistics
import random
import pandas as pd
import csv
df = pd.read_csv("data.csv")
data = df["temp"].tolist()
fig = ff.create_distplot([data], ["temp"], show_hist=False)
fig.show()
mean = statistics.mean(data)
std_deviation = statistics.stdev(data)
print(mean, std_deviation)
import pandas as pd
import plotly.figure_factory as ff
df = pd.read_csv("data.csv")
fig = ff.create_distplot([df["Avg Rating"]], ["Average Rating"],
show_hist=True)
fig.show()
import random
import plotly.express as px
import plotly.figure_factory as ff
count = []
diceResult = []
for i in range(0,100):
dice1 = random.randint(1,6)
dice2 = random.randint(1,6)
diceResult.append(dice1+dice2)
count.append(i)
#fig = px.bar(x = diceResult, y = count)
fig = ff.create_distplot([diceResult],["Result"],show_hist = False)
fig.show()
import plotly.figure_factory as ff
import csv
import pandas as pd
df = pd.read_csv("data.csv")
fig = ff.create_distplot([df["Weight(Pounds)"].tolist()], ["Weight"], show_hist= False)
fig.show()
def update_density(selected_group):
if selected_group != 0:
dense_plot = ff.create_distplot([vectors.iloc[:, selected_group - 1]],
[str(selected_group)])
dense_plot['layout'].update(title='<b>likelihood density</b>')
return dense_plot
mean = statistics.mean(mean_list)
print("mean of sampling distribution:- ", mean)
print("Standard deviation of sampling distribution:- ", std_deviation)
## findig the standard deviation starting and ending values
first_std_deviation_start, first_std_deviation_end = mean - std_deviation, mean + std_deviation
second_std_deviation_start, second_std_deviation_end = mean - (
2 * std_deviation), mean + (2 * std_deviation)
third_std_deviation_start, third_std_deviation_end = mean - (
3 * std_deviation), mean + (3 * std_deviation)
df = pd.read_csv("data.csv")
data = df["average"].tolist()
mean_of_sample1 = statistics.mean(data)
print("Mean of sample1:- ", mean_of_sample1)
fig = ff.create_distplot([mean_list], ["average"], show_hist=False)
fig.add_trace(
go.Scatter(x=[mean, mean], y=[0, 0.17], mode="lines", name="MEAN"))
fig.add_trace(
go.Scatter(x=[mean_of_sample1, mean_of_sample1],
y=[0, 0.17],
mode="lines",
name="Average of population"))
fig.add_trace(
go.Scatter(x=[first_std_deviation_end, first_std_deviation_end],
y=[0, 0.17],
mode="lines",
name="STANDARD DEVIATION 1 END"))
fig.add_trace(
go.Scatter(x=[second_std_deviation_end, second_std_deviation_end],
y=[0, 0.17],
import pandas as pd
import csv
import plotly.figure_factory as ff
df = pd.read_csv("bell.csv")
fig = ff.create_distplot([df["Avg Rating"].tolist()], ["Avg Rating"],
show_hist=False)
fig.show()
import os
import pandas as pd
import plotly.offline as pyo
import plotly.figure_factory as ff
import plotly.graph_objs as go
data_folder = os.path.join(os.path.dirname(os.path.dirname(__file__)),
'data_samples/Data')
data_file = os.path.join(data_folder, 'iris.csv')
df = pd.read_csv(data_file)
print(df['class'].unique())
x1 = df[df['class'] == 'Iris-setosa']['petal_length']
x2 = df[df['class'] == 'Iris-versicolor']['petal_length']
x3 = df[df['class'] == 'Iris-virginica']['petal_length']
hist_data = [x1, x2, x3]
group_labels = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
fig = ff.create_distplot(hist_data, group_labels)
pyo.plot(fig)
# Add labels
plt.title('Density plot and Histogram of number of words of abstract')
plt.xlabel('Count of documents')
plt.ylabel('Number of words')
plt.show()
# histogram
plt.hist(doc_length, color='blue', edgecolor='black', bins=size)
# Add labels
plt.title('Histogram of number of words of abstract')
plt.xlabel('Number of words')
plt.ylabel('Count of documents')
plt.show()
import plotly.figure_factory as ff
group_labels = ['distplot'] # name of the dataset
fig = ff.create_distplot([doc_length], group_labels)
py.plot(fig, filename='../schemas/preprocess_distplot_word_count.html')
# ======================================================================================================================
# Find the maximum length of abstract in the whole dataset
# ======================================================================================================================
print("Maximum length of abstract in the whole dataset",
max(data['abstract'].apply(len))) # 3011
print("Maximum length of title in the whole dataset",
max(data['title'].apply(len)))
# Maximum length of abstract in the whole dataset 1059
# Maximum length of title in the whole dataset 34
def create_distplot(*args, **kwargs):
FigureFactory._deprecated('create_distplot')
from plotly.figure_factory import create_distplot
return create_distplot(*args, **kwargs)
####### # This distplot demonstrates that random samples # seldom fit a "normal" distribution. ###### import plotly.offline as pyo import plotly.figure_factory as ff import numpy as np x1 = np.random.randn(200)-2 x2 = np.random.randn(200) x3 = np.random.randn(200)+2 x4 = np.random.randn(200)+4 hist_data = [x1,x2,x3,x4] group_labels = ['Group1','Group2','Group3','Group4'] fig = ff.create_distplot(hist_data, group_labels) pyo.plot(fig, filename='multiset_distplot.html')
def updateGraph(dataFields:list, filterIndex:int, graphType:int, binSize:int): """ updates the graph based on the chosen data fields, data filters, graph type, and bin size (the latter if histogram is selected) """ # title of the graph, set to the filename for now title = 'Without filter' if len(dataFields) == 0: return go.Figure(layout=dict(title=title)) # empty graph if filterIndex is 0: fList = ['isMale'] elif filterIndex is 1: fList = ['analyticMajor'] elif filterIndex is 2: fList = ['nativeEnglish'] # function which filters a piece of data # depending on the filters the user selected def dataFilter(data:dict) -> bool: for name in fList: return True filteredDataSet = tuple(filter(dataFilter, dataSet)) if len(filteredDataSet) == 0: return go.Figure(layout=dict(title=title)) # empty graph # convert the data being plotted into numbers try: traceValues = [ [ float(d[field]) for d in filteredDataSet ] for field in dataFields ] except ValueError: return go.Figure(layout=dict(title="Error: Can't plot non-numeric data on a numeric axis.")) # turn the position on the graph type slider into a graph type name graphType = GRAPHTYPE_CHOICES[graphType] if graphType == 'Histogram': out = ff.create_distplot( traceValues, dataFields, show_curve=False, show_rug=False, bin_size=binSize, ) out.layout['title'] = title return out if graphType == 'Density Plot': out = ff.create_distplot( traceValues, dataFields, show_hist=False, show_rug=False, ) out.layout['title'] = title return out layout = dict(title=title) # layout used by all of the graph types below if graphType == 'Violin Plot': traces = [ dict( type='violin', name=field, y=values, ) for field,values in zip(dataFields,traceValues) ] elif graphType == 'Box Plot': traces = [ go.Box( name=field, y=values, ) for field,values in zip(dataFields,traceValues) ] elif graphType == 'Dot Plot': traces = [ dict( type='scatter', name=field, y=[d[field] for d in filteredDataSet], x=[d[DATA_IDFIELD] for d in filteredDataSet], mode='markers', ) for field in dataFields ] layout['xaxis'] = dict( title=DATA_IDFIELD, type='category', titlefont=dict( size=12, ), ) elif graphType == 'Bar Plot': traces = [ go.Bar( name=field, y=[d[field] for d in filteredDataSet], x=[d[DATA_IDFIELD] for d in filteredDataSet], ) for field in dataFields ] layout['xaxis'] = dict( title=DATA_IDFIELD, type='category', titlefont=dict( size=12, ), ) return go.Figure(data=traces, layout=layout)
####### # This distplot looks back at the Mark Twain/ # Quintus Curtius Snodgrass data and tries # to compare them. ###### import plotly.offline as pyo import plotly.figure_factory as ff snodgrass = [.209,.205,.196,.210,.202,.207,.224,.223,.220,.201] twain = [.225,.262,.217,.240,.230,.229,.235,.217] hist_data = [snodgrass,twain] group_labels = ['Snodgrass','Twain'] fig = ff.create_distplot(hist_data, group_labels, bin_size=[.005,.005]) pyo.plot(fig, filename='SnodgrassTwainDistplot.html')
import statistics as st
import csv
import plotly_express as px
import plotly.figure_factory as ff
import pandas as pd
df = pd.read_csv("StudentsPerformance.csv")
reading_score = df["reading score"].tolist()
fig = ff.create_distplot([reading_score], ["reading score"], show_hist=False)
fig.show()
mean = st.mean(reading_score)
print("mean:", mean)
std = st.stdev(reading_score)
print("standard deviation:", std)
SD1_START, SD1_END = mean - std, mean + std
SD2_START, SD2_END = mean - (2 * std), mean - (2 * std)
SD3_START, SD3_END = mean - (3 * std), mean - (3 * std)
listdata_1SD = [
result for result in reading_score
if result > SD1_START and result < SD1_END
]
listdata_2SD = [
result for result in reading_score
if result > SD2_START and result < SD2_END
]
listdata_3SD = [
result for result in reading_score
if result > SD3_START and result < SD3_END
]
print("{}% of data lies between 1SD".format(
len(listdata_1SD) * 100.0 / len(reading_score)))
def genFigure(xCfgAirlines, xCfgLocations, xCfgAircraft, normalized):
########################################
########################################
selectedAirports = xCfgAirlines.get('airports', dataModule.Airports)
selectedAirlines = xCfgAirlines.get('airlines', dataModule.Airlines)
# selectedAircraft = xCfgAircraft.get('aircraft', dataModule.Aircraft)
selectedAircraft = xCfgAircraft
routes = dataModule.filterData(selectedAirports, selectedAirlines, selectedAircraft)
# YlOrRd = cl.scales['9']['seq']['YlOrRd']
# clrscale = cl.to_rgb(cl.interp( YlOrRd, 10 ))
rangeData = []
groupLabels = []
for ac, df in routes.groupby('aircraft'):
distances = df['distance'].values
if len(distances) < 3: continue
ac = ac.replace('Boeing ', 'B').replace('Airbus ', '').replace('McDonnell Douglas ', '').replace('Embraer ', 'E').replace('Aerospatiale/Alenia ','')
groupLabels += [ac[0:20]] #max 20 characters
m = np.mean(distances) if 'yes' in normalized else 1
rangeData += [distances/m]
fig = ff.create_distplot(rangeData, groupLabels,
bin_size=100, show_hist = False, show_rug = False, histnorm='probability') #density
fig = fig.to_dict()
for i, d in enumerate(fig['data']):
d['opacity'] = 0.6
d['selectgroup'] = i
d['selectedpoints'] = [0]
fig['layout'].update( dict(
title = 'Distances Flown by Aircraft Type',
titlefont = {
'size': 16,
'color': '#a8a8a8',
'family': 'Open Sans'
},
font = {'color': '#fff',},
xaxis = dict(
type='log',
showgrid=True,
gridcolor='rgba(255,255,255,.2)',
tickfont={'color':'white'},
title= 'Normalized Distance',
titlefont= {'color': '#a8a8a8'}),
yaxis=dict(
showgrid=False,
showticklabels=True,
ticks='',
tickfont={'color':'white'},
visibile=True,
title= 'Prob. Density',
titlefont={'color':'#a8a8a8'}
),
paper_bgcolor='rgba(0,0,0,0)',
plot_bgcolor='rgba(0,0,0,0)',
margin={'t': 40, 'b':40 , 'r':0, 'l': 50, 'pad': 1},
legend={'orientation':'v', 'xanchor': 'left', 'x': 1},
))
return fig
def normalize_series(dframe, series_col_index):
y = dframe[series_col_index]
log_y = np.log(y)
diff_log_y = log_y - np.average(log_y)
var_log_y = sum(diff_log_y**2) / len(y)
stdev_log_y = np.sqrt(var_log_y)
cnt = 0
for i in range(0, len(log_y)):
if (abs(diff_log_y[i]) > (4 * stdev_log_y)):
cnt += 1
if (i > 5):
y.iloc[i] = y.iloc[i - 1]
else:
y.iloc[i] = y.iloc[i + 1]
#print('cleaned: ', cnt)
dframe = pd.read_csv(sys.argv[1]) #index_col=0
hist_data = [
dframe['1thread'], dframe['2thread'], dframe['3thread'], dframe['4thread'],
dframe['5thread'], dframe['6thread'], dframe['7thread'], dframe['8thread']
]
group_labels = [
'Single_Threaded', '2_Threads', '3_Threads', '4_Threads', '5_Threads',
'6_Threads', '7_Threads', '8_Threads'
]
fig = ff.create_distplot(hist_data, group_labels, show_hist=False)
div1 = plotly.offline.plot(fig, include_plotlyjs=False, output_type='div')
print(div1)
def show_fig(mean_list):
df = mean_list
fig = ff.create_distplot([df], ["reading_time"])
fig.show()
def showFig(meanList):
df = meanList
fig = pf.create_distplot([df], ["Reading Time"], show_hist=False)
fig.show()