def plot_chord_chart(nodes, links):
"""Plot a chord chart."""
lg.info("Plotting chart ...")
# Turn dict of vertices and chords into DataFrames
nodes_df = pd.DataFrame(nodes)
links_df = pd.DataFrame(links)
# Merge DataFrames into source data
source_data = links_df.merge(nodes_df,
how="left",
left_on="source",
right_index=True)
source_data = source_data.merge(nodes_df,
how="left",
left_on="target",
right_index=True)
# Create chord chart
chord_from_df = Chord(source_data,
source="name_x",
target="name_y",
value="value")
# Create chord chart file as html
output_file("chord_from_df.html", mode="inline")
# Show chart
show(chord_from_df)
def plot_chord(df, names):
# Cleaning up received DataFrame
df = organize(df)
df = df[['family_id', 'region_id']]
tf = df.drop_duplicates(keep='first')
tl = df.drop_duplicates(keep='last')
df = pd.concat([tf, tl])
# Generating nodes and links
cnxns = []
for k, g in df.groupby('family_id'):
[
cnxns.extend(
(n1, n2, len(g)) for n1, n2 in combinations(g['region_id'], 2))
]
df = pd.DataFrame(cnxns, columns=['region1', 'region2', 'total'])
df = df.groupby(['region1', 'region2']).agg('sum')
df = df.reset_index()
# Chord won't work with duplicated places
df = df[df.region1 != df.region2]
# Using only most relevant links
df = df[df.total > 100]
# Associating names
df = pd.merge(df,
names,
how='inner',
left_on='region1',
right_on='cod_mun')
df = df[['region2', 'total', 'cod_name']]
df = pd.merge(df,
names,
how='inner',
left_on='region2',
right_on='cod_mun')
df = df[['cod_name_x', 'cod_name_y', 'total']]
# Making and saving and showing Chord
chord = Chord(df, source='cod_name_x', target='cod_name_y', value='total')
output_file('chord.html', mode='inline')
show(chord)
values='pulse',
label='diet',
color='diet',
title='exercise dataset')
box2 = BoxPlot(data=exercise,
values='pulse',
label='diet',
stack='kind',
color='kind',
title='exercise dataset')
show(row(box1, box2))
# In[6]:
# 弦图 Chord
chord1 = Chord(data=exercise, source="id", target="kind")
chord2 = Chord(data=exercise, source="id", target="kind", value="pulse")
show(row(chord1, chord2))
# * bokeh.plotting
# In[7]:
from bokeh.plotting import figure
import numpy as np
p = figure(plot_width=400, plot_height=400)
# 方框
p.square(np.random.randint(1, 10, 5),
np.random.randint(1, 10, 5),
Freq = trips.groupby(["Start station",
"End station"]).size().reset_index(name="Frequency")
# Set the stations as nodes and the number of trips as links
nodes_df = pd.DataFrame(Station)
links_df = pd.DataFrame(Freq)
# Left join node and link dataframes
source_data = links_df.merge(nodes_df,
how='left',
left_on='Start station',
right_index=True)
source_data = source_data.merge(nodes_df,
how='left',
left_on='End station',
right_index=True)
# Find high-traffic stations
source_data = source_data[source_data["Frequency"] > 3500]
# Define chord chart
StationChord = Chord(source_data,
source="Start station",
target="End station",
value="Frequency")
# Write output file
output_file('StationChord.html', mode="inline")
# Show chord chart
show(StationChord)
@author: homemdasneves
"""
# create a chord diagram with relationships between bootcampers
import random
import pandas as pd
import matplotlib as plt
from bokeh.io import show
from bokeh.charts import Chord
path = "C:\\work\\projetos\\ie-ds-bootcamp\\ie-ds-bc-group3\\data\\"
data = pd.read_csv(path + "Aug_2017.csv")
aux = data.head(5)
NUM_ORIG_DESTS = 50
SORT_BY_AVG = "ARR_DELAY"
data_aux = data.groupby(by=["ORIGIN", "DEST"], as_index=False).mean() \
.sort_values(by = [SORT_BY_AVG], ascending=[False]).head(NUM_ORIG_DESTS)
data_aux[SORT_BY_AVG + "_INT"] = data_aux[SORT_BY_AVG].astype(int)
chord_from_df2 = Chord(data_aux,
source="ORIGIN",
target="DEST",
value=SORT_BY_AVG + "_INT")
show(chord_from_df2)
import pandas as pd #导入pandas，用于操作excel文件
from bokeh.charts import output_file, Chord #导入bokeh扩展包，用于绘制弦图
from bokeh.io import show #导入文件操作中的显示网页函数
df=pd.read_excel('Chord.xlsx')#打开excel文件
my_links=[] #备用空列表
for i in range(len(df.columns)):#外层循环，轮询excel每个列
# print(df[df.columns[i]])
for j in range(len(df.index)):#内层循环，轮询excel每一行
my_links.append({'target':(i+len(df.index)),'source':j,'value':df[df.columns[i]][j]})#生成从源到目标的字典,target跳过ABC
index=list(df.index)#将excel行标签转化为列表
index.extend(df.columns)#合并列表，得到所有标签
my_nodes=pd.DataFrame([{'name':i} for i in index])#生成节点数据框
my_nodes_df = pd.DataFrame(my_nodes)#生成用于绘图的节点数据
my_links_df = pd.DataFrame(my_links)#生成用于绘图的节点间连接
my_source_data = my_links_df.merge(my_nodes_df, how='left',
left_on='source', right_index=True)#合并数据，顺序按从源到目标的顺序
my_source_data = my_source_data.merge(my_nodes_df, how='left',
left_on='target', right_index=True)#再次合并数据，顺序按从目标到源的顺序
chord_from_df = Chord(my_source_data, source="name_x", target="name_y", value="value")#绘制弦图
output_file('my_chord-diagram.html')#当前文件夹输出网页文件
show(chord_from_df)#显示图片
links_df['group_x'] = links_df['gate-name'].map(
gates) # group of the first gate
links_df['group_y'] = links_df['next-gate'].map(
gates) # group of the second gate
links_df = links_df[links_df['count'] >
5] # only select those with more than 5 transactions
links_df = links_df[links_df['gate-name'] != links_df['next-gate']]
from bokeh.charts import output_file, Chord
from bokeh.io import show
import bokeh
chord_from_df = Chord(links_df,
source='gate-name',
target='next-gate',
value='count')
chord_from_df.plot_height = 1000
chord_from_df.plot_width = 1000
output_file('chord-diagram.html')
show(chord_from_df)
# okay so this kinda looks pretty crap
# plan 2: assign each gate name an index
gateIndex = {}
for i, j in enumerate(gates.keys()):
gateIndex[j] = i
links_df['source'] = links_df['gate-name'].map(gateIndex)
links_df['target'] = links_df['next-gate'].map(gateIndex)
from bokeh.charts import output_file, Chord
from bokeh.io import show
import pandas as pd
data = pd.read_csv('../../samples/test3.csv')
chord_from_df = Chord(data, source='name_x', target='name_y', value='value')
output_file('chord.html')
show(chord_from_df)