Cannot create secondary x-axis with xlsxwriter - python

I am trying to generate a chart with a secondary x-axis, but I can't get the secondary x-axis to be added to the chart.
Below is the code I'm using. If I change "x2_axis" to "y2_axis" and "set_x2_axis" to "set_y2_axis", then I am able to create a secondary y axis successfully -- but it does not work for a secondary x axis. Am I doing something wrong?
import xlsxwriter
workbook = xlsxwriter.Workbook('test.xlsx')
worksheet = workbook.add_worksheet()
data = [
[1, 2, 3, 4, 5],
[10, 40, 50, 20, 10],
[1,1,2,2,3,3,4,4,5,5],
[200,200,100,100,300,300,250,250,350,350]
]
worksheet.write_column('A2', data[0])
worksheet.write_column('B2', data[1])
worksheet.write_column('C2', data[2])
worksheet.write_column('D2', data[3])
chart= workbook.add_chart({'type': 'line'})
chart.add_series ({
'name': 'Primary',
'categories': '=Sheet1!$A$2:$A$6',
'values': '=Sheet1!$B$2:$B$6',
})
chart.add_series ({
'name': 'Secondary',
'categories': '=Sheet1!$C$2:$C$11',
'values': '=Sheet1!$D$2:$D$11',
'x2_axis': True
})
chart.set_x_axis({
'name': 'Primary Axis',
'interval_unit': 1,
'interval_tick': 1,
'major_tick_mark': 'none',
})
chart.set_y_axis({
'name': 'Value',
})
chart.set_x2_axis({
'label_position': 'low',
'name': 'Secondary Axis',
'visible': True
})
worksheet.insert_chart('B20', chart)
workbook.close()

Setting a secondary X axis in Excel (or XlsxWriter) isn't obvious, in comparison to setting a secondary Y axis. Generally, you need to add a secondary Y and X axis pair before you can set a secondary X axis. Something like this:
import xlsxwriter
workbook = xlsxwriter.Workbook('test.xlsx')
worksheet = workbook.add_worksheet()
data = [
[1, 2, 3, 4, 5],
[10, 40, 50, 20, 10],
[1, 1, 2, 2, 3, 3, 4, 4, 5, 5],
[200, 200, 100, 100, 300, 300, 250, 250, 350, 350]
]
worksheet.write_column('A2', data[0])
worksheet.write_column('B2', data[1])
worksheet.write_column('C2', data[2])
worksheet.write_column('D2', data[3])
chart = workbook.add_chart({'type': 'line'})
chart.add_series({
'name': 'Primary',
'categories': '=Sheet1!$A$2:$A$6',
'values': '=Sheet1!$B$2:$B$6',
})
chart.add_series({
'name': 'Secondary',
'categories': '=Sheet1!$C$2:$C$11',
'values': '=Sheet1!$D$2:$D$11',
'x2_axis': True,
'y2_axis': True,
})
chart.set_x_axis({
'name': 'Primary Axis',
'interval_unit': 1,
'interval_tick': 1,
'major_tick_mark': 'none',
})
chart.set_y_axis({
'name': 'Y Values 1',
})
chart.set_y2_axis({
'name': 'Y Values 2',
'crossing': 'max',
})
chart.set_x2_axis({
'label_position': 'high',
'name': 'Secondary Axis',
'visible': True,
})
worksheet.insert_chart('B20', chart)
workbook.close()
Output:

Related

Extract key and value from json to new dataframe

I have a dataframe that has JSON values are in columns. Those were indented into multiple levels. I would like to extract the end key and value into a new dataframe. I will give you sample column values below
{'shipping_assignments': [{'shipping': {'address': {'address_type':
'shipping', 'city': 'Calder', 'country_id': 'US',
'customer_address_id': 1, 'email': 'roni_cost#example.com',
'entity_id': 1, 'firstname': 'Veronica', 'lastname': 'Costello',
'parent_id': 1, 'postcode': '49628-7978', 'region': 'Michigan',
'region_code': 'MI', 'region_id': 33, 'street': ['6146 Honey Bluff
Parkway'], 'telephone': '(555) 229-3326'}, 'method':
'flatrate_flatrate', 'total': {'base_shipping_amount': 5,
'base_shipping_discount_amount': 0,
'base_shipping_discount_tax_compensation_amnt': 0,
'base_shipping_incl_tax': 5, 'base_shipping_invoiced': 5,
'base_shipping_tax_amount': 0, 'shipping_amount': 5,
'shipping_discount_amount': 0,
'shipping_discount_tax_compensation_amount': 0, 'shipping_incl_tax':
5, 'shipping_invoiced': 5, 'shipping_tax_amount': 0}}, 'items':
[{'amount_refunded': 0, 'applied_rule_ids': '1',
'base_amount_refunded': 0, 'base_discount_amount': 0,
'base_discount_invoiced': 0, 'base_discount_tax_compensation_amount':
0, 'base_discount_tax_compensation_invoiced': 0,
'base_original_price': 29, 'base_price': 29, 'base_price_incl_tax':
31.39, 'base_row_invoiced': 29, 'base_row_total': 29, 'base_row_total_incl_tax': 31.39, 'base_tax_amount': 2.39,
'base_tax_invoiced': 2.39, 'created_at': '2019-09-27 10:03:45',
'discount_amount': 0, 'discount_invoiced': 0, 'discount_percent': 0,
'free_shipping': 0, 'discount_tax_compensation_amount': 0,
'discount_tax_compensation_invoiced': 0, 'is_qty_decimal': 0,
'item_id': 1, 'name': 'Iris Workout Top', 'no_discount': 0,
'order_id': 1, 'original_price': 29, 'price': 29, 'price_incl_tax':
31.39, 'product_id': 1434, 'product_type': 'configurable', 'qty_canceled': 0, 'qty_invoiced': 1, 'qty_ordered': 1,
'qty_refunded': 0, 'qty_shipped': 1, 'row_invoiced': 29, 'row_total':
29, 'row_total_incl_tax': 31.39, 'row_weight': 1, 'sku':
'WS03-XS-Red', 'store_id': 1, 'tax_amount': 2.39, 'tax_invoiced':
2.39, 'tax_percent': 8.25, 'updated_at': '2019-09-27 10:03:46', 'weight': 1, 'product_option': {'extension_attributes':
{'configurable_item_options': [{'option_id': '141', 'option_value':
167}, {'option_id': '93', 'option_value': 58}]}}}]}],
'payment_additional_info': [{'key': 'method_title', 'value': 'Check /
Money order'}], 'applied_taxes': [{'code': 'US-MI--Rate 1', 'title':
'US-MI--Rate 1', 'percent': 8.25, 'amount': 2.39, 'base_amount':
2.39}], 'item_applied_taxes': [{'type': 'product', 'applied_taxes': [{'code': 'US-MI--Rate 1', 'title': 'US-MI--Rate 1', 'percent':
8.25, 'amount': 2.39, 'base_amount': 2.39}]}], 'converting_from_quote': True}
Above is single row value of the dataframe column df['x']
My codes are below to convert
sample = data['x'].tolist()
data = json.dumps(sample)
df = pd.read_json(data)
it gives new dataframe with columns
Index(['applied_taxes', 'converting_from_quote', 'item_applied_taxes',
'payment_additional_info', 'shipping_assignments'],
dtype='object')
When I tried to do the same above to convert the column which has row values
m_df = df['applied_taxes'].apply(lambda x : re.sub('.?\[|$.|]',"", str(x)))
m_sample = m_df.tolist()
m_data = json.dumps(m_sample)
c_df = pd.read_json(m_data)
It doesn't work
Check this link to get the beautified_json
I came across a beautiful ETL package in python called petl. convert the json list into dict form with the help of function called fromdicts(json_string)
order_table = fromdicts(data_list)
If you find any nested dict in any of the columns, use unpackdict(order_table,'nested_col')
it will unpack the nested dict.
In my case, I need to unpack the applied_tax column. Below code will unpack and append the key and value as a column and row in the same table.
order_table = unpackdict(order_table, 'applied_taxes')
If you guys wants to know more about -petl
It seems that your mistake was in tolist(). Try the following:
import pandas as pd
import json
import re
data = {"shipping_assignments":[{"shipping":{"address":{"address_type":"shipping","city":"Calder","country_id":"US","customer_address_id":1,"email":"roni_cost#example.com","entity_id":1,"firstname":"Veronica","lastname":"Costello","parent_id":1,"postcode":"49628-7978","region":"Michigan","region_code":"MI","region_id":33,"street":["6146 Honey Bluff Parkway"],"telephone":"(555) 229-3326"},"method":"flatrate_flatrate","total":{"base_shipping_amount":5,"base_shipping_discount_amount":0,"base_shipping_discount_tax_compensation_amnt":0,"base_shipping_incl_tax":5,"base_shipping_invoiced":5,"base_shipping_tax_amount":0,"shipping_amount":5,"shipping_discount_amount":0,"shipping_discount_tax_compensation_amount":0,"shipping_incl_tax":5,"shipping_invoiced":5,"shipping_tax_amount":0}},"items":[{"amount_refunded":0,"applied_rule_ids":"1","base_amount_refunded":0,"base_discount_amount":0,"base_discount_invoiced":0,"base_discount_tax_compensation_amount":0,"base_discount_tax_compensation_invoiced":0,"base_original_price":29,"base_price":29,"base_price_incl_tax":31.39,"base_row_invoiced":29,"base_row_total":29,"base_row_total_incl_tax":31.39,"base_tax_amount":2.39,"base_tax_invoiced":2.39,"created_at":"2019-09-27 10:03:45","discount_amount":0,"discount_invoiced":0,"discount_percent":0,"free_shipping":0,"discount_tax_compensation_amount":0,"discount_tax_compensation_invoiced":0,"is_qty_decimal":0,"item_id":1,"name":"Iris Workout Top","no_discount":0,"order_id":1,"original_price":29,"price":29,"price_incl_tax":31.39,"product_id":1434,"product_type":"configurable","qty_canceled":0,"qty_invoiced":1,"qty_ordered":1,"qty_refunded":0,"qty_shipped":1,"row_invoiced":29,"row_total":29,"row_total_incl_tax":31.39,"row_weight":1,"sku":"WS03-XS-Red","store_id":1,"tax_amount":2.39,"tax_invoiced":2.39,"tax_percent":8.25,"updated_at":"2019-09-27 10:03:46","weight":1,"product_option":{"extension_attributes":{"configurable_item_options":[{"option_id":"141","option_value":167},{"option_id":"93","option_value":58}]}}}]}],"payment_additional_info":[{"key":"method_title","value":"Check / Money order"}],"applied_taxes":[{"code":"US-MI-*-Rate 1","title":"US-MI-*-Rate 1","percent":8.25,"amount":2.39,"base_amount":2.39}],"item_applied_taxes":[{"type":"product","applied_taxes":[{"code":"US-MI-*-Rate 1","title":"US-MI-*-Rate 1","percent":8.25,"amount":2.39,"base_amount":2.39}]}],"converting_from_quote":"True"}
df = pd.read_json(json.dumps(data))
m_df = df['applied_taxes'].apply(lambda x : re.sub('.?\[|$.|]',"", str(x)))
c_df = pd.read_json(json.dumps(list(m_df)))
print(c_df)
prints the following:
0
0 {'code': 'US-MI-*-Rate 1', 'title': 'US-MI-*-R...

Plotly vertical line with legend in python

In plotly website, there is example that can use shape function add vertical or horizontal line in plotly.
import plotly.plotly as py
import plotly.graph_objs as go
trace0 = go.Scatter(
x=[2, 3.5, 6],
y=[1, 1.5, 1],
mode='text',
)
data = [trace0]
layout = {
'xaxis': {
'range': [0, 7]
},
'yaxis': {
'range': [0, 2.5]
},
'shapes': [
# Line Horizontal
{
'type': 'line',
'x0': 2,
'y0': 2,
'x1': 5,
'y1': 2,
'line': {
'color': 'rgb(50, 171, 96)',
'width': 4,
'dash': 'dashdot',
}
}
]
}
fig = {
'data': data,
'layout': layout,
}
py.iplot(fig, filename='shapes-lines')
But I wonder if there is any ways to add legend for the horizontal lines.
I think the only option at the moment is to plot it as a Scatter trace.
For example this snippet of code
import plotly.graph_objects as pgo
fig = pgo.Figure()
fig.add_traces([
pgo.Scatter(
x=[2, 3.5, 6],
y=[1, 1.5, 1],
name='Yet Another Trace'
),
pgo.Scatter(
x=[2,5],
y=[2,2],
line={
'color': 'rgb(50, 171, 96)',
'width': 4,
'dash': 'dashdot',
}, name='Horizontal Line'
)
])
fig.update_layout(**{
'xaxis': {
'range': [0, 7]
},
'yaxis': {
'range': [0, 2.5]
}
})
fig
generates this result:

Increasing opacity of area plot in plotly

How do I increase the opacity or alpha of the 'filled' area of my plot? I tried:
import pandas as pd
import plotly.offline as py
import plotly.graph_objs as go
import cufflinks as cf
from plotly import tools
plotly.offline.init_notebook_mode()
cf.go_offline()
df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df.iplot(kind='area', fill=True, filename='cuflinks/stacked-area', opacity=.1)
but it doesn't seem to work.
There doesn't seem to be an easy built-in way of achieving this. However, a work-around is to first get the figure object of the plot, modify it to change the opacity, and then plot it.
You can get the figure object using the asFigure attribute like this:
figure = df.iplot(asFigure=True, kind='area', fill=True, filename='cuflinks/stacked-area')
The figure object in this case looks like:
Figure({
'data': [{'fill': 'tonexty',
'fillcolor': 'rgba(255, 153, 51, 0.3)',
'line': {'color': 'rgba(255, 153, 51, 1.0)', 'dash': 'solid', 'shape': 'linear', 'width': 1.3},
'mode': 'lines',
'name': 'a',
'text': '',
'type': 'scatter',
'uid': '4dcc1a3e-fba3-4a32-bb2a-40925b4fae5b',
'x': array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=int64),
'y': array([0.91229144, 0.63049138, 0.22855077, 0.13470399, 0.9114691 , 0.39640368,
0.46534334, 0.20508211, 0.00203548, 0.41343938])},
{'fill': 'tonexty',
'fillcolor': 'rgba(55, 128, 191, 0.3)',
'line': {'color': 'rgba(55, 128, 191, 1.0)', 'dash': 'solid', 'shape': 'linear', 'width': 1.3},
'mode': 'lines',
'name': 'b',
'text': '',
'type': 'scatter',
'uid': '1015b30d-7c09-456c-875c-8a211a6ebdeb',
'x': array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=int64),
'y': array([1.81115175, 1.57534372, 0.41288126, 0.38068805, 1.72268856, 0.87778503,
1.32714727, 0.848242 , 0.51605283, 0.58190402])},
{'fill': 'tonexty',
'fillcolor': 'rgba(50, 171, 96, 0.3)',
'line': {'color': 'rgba(50, 171, 96, 1.0)', 'dash': 'solid', 'shape': 'linear', 'width': 1.3},
'mode': 'lines',
'name': 'c',
'text': '',
'type': 'scatter',
'uid': '7d1852ac-b8e7-44e6-ae69-54229d7e2c83',
'x': array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=int64),
'y': array([2.79222081, 1.58812634, 1.1439478 , 1.30453731, 2.50881795, 1.67681961,
1.85609861, 1.36657712, 0.89024486, 0.82749039])},
{'fill': 'tonexty',
'fillcolor': 'rgba(128, 0, 128, 0.3)',
'line': {'color': 'rgba(128, 0, 128, 1.0)', 'dash': 'solid', 'shape': 'linear', 'width': 1.3},
'mode': 'lines',
'name': 'd',
'text': '',
'type': 'scatter',
'uid': '89b85012-fc95-487c-b7ba-9cb6c249b768',
'x': array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=int64),
'y': array([3.54740551, 1.79856232, 2.1326556 , 2.10560567, 2.64867039, 2.55519564,
2.73888819, 2.23274393, 1.16987343, 1.42794202])}],
'layout': {'legend': {'bgcolor': '#F5F6F9', 'font': {'color': '#4D5663'}},
'paper_bgcolor': '#F5F6F9',
'plot_bgcolor': '#F5F6F9',
'title': {'font': {'color': '#4D5663'}},
'xaxis': {'gridcolor': '#E1E5ED',
'showgrid': True,
'tickfont': {'color': '#4D5663'},
'title': {'font': {'color': '#4D5663'}, 'text': ''},
'zerolinecolor': '#E1E5ED'},
'yaxis': {'gridcolor': '#E1E5ED',
'showgrid': True,
'tickfont': {'color': '#4D5663'},
'title': {'font': {'color': '#4D5663'}, 'text': ''},
'zerolinecolor': '#E1E5ED'}}
})
You'll note that each trace in the data has a fillcolor attribute: 'fillcolor': 'rgba(255, 153, 51, 0.3)'. The last number is the alpha value, which you want to modify. I've made a hacky little function to update the fillcolor attribute of all traces in a figure object:
def update_opacity(figure,opacity):
for trace in range(len(figure['data'])):
# print(figure['data'][trace]['fillcolor'],'-> ',end='')
rgba_split = figure['data'][trace]['fillcolor'].split(',')
figure['data'][trace]['fillcolor'] = ','.join(rgba_split[:-1] + [' {})'.format(opacity)])
# print(figure['data'][trace]['fillcolor'])
return figure
For full opacity, you can do:
figure = update_opacity(figure,1)
Then, simply plot the result with
py.iplot(figure)
Output:

Interactive Plotly Barchart

I am attempting to adapt the Python Plotly example on 'Adding Sliders to Animations in Python' to a barchart but am getting a 'Figure field is invalid' message.
I am trying to adapt the input data to reflect that of a bar chart rather than a scatter chart (used in the example). I have created a grid:
Which I am using with the following code:
years = ['2007','2008','2009']
items = ['Name_1','Name_2']
col_name_template = '{column}'
for year in years:
frame = {'data': [], 'name': str(year)}
x_list = []
y_list = []
for item in items:
x_list.append(grid.get_column_reference(col_name_template.format(column='name')))
y_list.append(grid.get_column_reference(col_name_template.format(column=year)))
frame['data'].append(go.Bar(
x=x_list,
y=y_list
))
figure['frames'].append(frame)
slider_step = {'args': [
[year],
{'frame': {'duration': 300, 'redraw': False},
'mode': 'immediate',
'transition': {'duration': 300}}
],
'label': year,
'method': 'animate'}
sliders_dict['steps'].append(slider_step)
figure['layout']['sliders'] = [sliders_dict]
py.icreate_animations(figure, 'barchart example')
When trying to plot I get the following error:
Figure field is invalid. Reason: Raw data arrays are not allowed at this endpoint. Use grid references instead. Raw data found at the following paths in the figure...
How do I use only grid references but also ensure that a bar chart is plotted rather than a scatter chart?
I used the offline method of plotting plotly.offline.iplot which doesn't require grid references. The only downside of animations with bar charts is that transitions aren't currently supported.
Code below (including buttons and slider):
from plotly.offline import init_notebook_mode, iplot
from IPython.display import display, HTML
init_notebook_mode(connected = True)
years = ['2010', '2011', '2012']
items = ['A', 'B', 'C', 'D']
count = [
[1, 2, 3, 4],
[2, 3, 4, 1],
[3, 4, 1, 2]
]
figure = {
'data': [{
'type': 'bar',
'x': items,
'y': count[0]
}],
'layout': {
'xaxis': {
'title': 'X',
'gridcolor': '#FFFFFF',
'linecolor': '#000',
'linewidth': 1,
'zeroline': False,
'autorange': False
},
'yaxis': {
'title': 'Y',
'gridcolor': '#FFFFFF',
'linecolor': '#000',
'linewidth': 1,
'range': [0, 5],
'autorange': False
},
'title': 'Example Title',
'hovermode': 'closest',
'updatemenus': [{
'type': 'buttons',
'buttons': [{
'label': 'Play',
'method': 'animate',
'args': [None, {
'frame': {
'duration': 500,
'redraw': True
},
'fromcurrent': True,
'transition': {
'duration': 300,
'easing': 'quadratic-in-out'
}
}]
},
{
'label': 'End',
'method': 'animate',
'args': [None, {
'frame': {
'duration': 0,
'redraw': True
},
'fromcurrent': True,
'mode': 'immediate',
'transition': {
'duration': 0
}
}]
}
],
'direction': 'left',
'pad': {
'r': 10,
't': 87
},
'showactive': False,
'type': 'buttons',
'x': 0.1,
'xanchor': 'right',
'y': 0,
'yanchor': 'top'
}]
},
'frames': []
}
sliders_dict = {
'active': 0,
'yanchor': 'top',
'xanchor': 'left',
'currentvalue': {
'font': {
'size': 20
},
'prefix': 'Year:',
'visible': True,
'xanchor': 'right'
},
'transition': {
'duration': 300,
'easing': 'cubic-in-out'
},
'pad': {
'b': 10,
't': 50
},
'len': 0.9,
'x': 0.1,
'y': 0,
'steps': []
}
for index, year in enumerate(years):
frame = {
'data': [{
'type': 'bar',
'x': items,
'y': count[index]
}],
'name': str(year)
}
figure['frames'].append(frame)
slider_step = {
'args': [
[year],
{
'frame': {
'duration': 300,
'redraw': True
},
'mode': 'immediate',
'transition': {
'duration': 300
}
}
],
'label': year,
'method': 'animate'
}
sliders_dict['steps'].append(slider_step)
figure['layout']['sliders'] = [sliders_dict]
iplot(figure)

Adding node elements to json object in Python from NetworkX

I have a json object that I made using networkx:
json_data = json_graph.node_link_data(network_object)
It is structured like this (mini version of my output):
>>> json_data
{'directed': False,
'graph': {'name': 'compose( , )'},
'links': [{'source': 0, 'target': 7, 'weight': 1},
{'source': 0, 'target': 2, 'weight': 1},
{'source': 0, 'target': 12, 'weight': 1},
{'source': 0, 'target': 9, 'weight': 1},
{'source': 2, 'target': 18, 'weight': 25},
{'source': 17, 'target': 25, 'weight': 1},
{'source': 29, 'target': 18, 'weight': 1},
{'source': 30, 'target': 18, 'weight': 1}],
'multigraph': False,
'nodes': [{'bipartite': 1, 'id': 'Icarus', 'node_type': 'Journal'},
{'bipartite': 1,
'id': 'A Giant Step: from Milli- to Micro-arcsecond Astrometry',
'node_type': 'Journal'},
{'bipartite': 1,
'id': 'The Astrophysical Journal Supplement Series',
'node_type': 'Journal'},
{'bipartite': 1,
'id': 'Astronomy and Astrophysics Supplement Series',
'node_type': 'Journal'},
{'bipartite': 1, 'id': 'Astronomy and Astrophysics', 'node_type': 'Journal'},
{'bipartite': 1,
'id': 'Astronomy and Astrophysics Review',
'node_type': 'Journal'}]}
What I want to do is add the following elements to each of the nodes so I can use this data as an input for sigma.js:
"x": 0,
"y": 0,
"size": 3
"centrality": 0
I can't seem to find an efficient way to do this though using add_node(). Is there some obvious way to add this that I'm missing?
While you have your data as a networkx graph, you could use the set_node_attributes method to add the attributes (e.g. stored in a python dictionary) to all the nodes in the graph.
In my example the new attributes are stored in the dictionary attr:
import networkx as nx
from networkx.readwrite import json_graph
# example graph
G = nx.Graph()
G.add_nodes_from(["a", "b", "c", "d"])
# your data
#G = json_graph.node_link_graph(json_data)
# dictionary of new attributes
attr = {"x": 0,
"y": 0,
"size": 3,
"centrality": 0}
for name, value in attr.items():
nx.set_node_attributes(G, name, value)
# check new node attributes
print(G.nodes(data=True))
You can then export the new graph in JSON with node_link_data.

Categories

Resources