I have some names and scores as follows
input = {
'Maths': dict(Mohsen=19, Sadegh=18, Hafez=15),
'Physics': dict(Sadegh=16, Hafez=17, Mohsen=17),
'Chemistry': dict(Hafez=13),
'Literature': dict(Sadegh=14),
'Biology': dict(Mohsen=16, Sadegh=10),
}
if a person don't have any lesson its score consider zero also get avrege of scores's person and sort final list by averge and i want to get an output like this.
answer = [
dict(Name='Sadegh', Literature=14, Chemistry=0, Maths=18, Physics=16, Biology=10, Average=11.6),
dict(Name='Mohsen', Maths=19, Physics=17, Chemistry=0, Biology=16, Literature=0, Average=10.4),
dict(Name='Hafez', Chemistry=13, Biology=0, Physics=17, Literature=0, Maths=15, Average=9),
]
how to do it?
Essentially, you have a dictionary, where the information is arranged based on subjects, where for each subject, you have student marks. You want to collection all information related to each student in separate dictionaries.
One of the approaches which can try, is as below:
Try converting the data which you have into student specific data and then you can calculate the Average of the Marks of all subjects for that student. There is a sample code below.
Please do note that, this is just a sample and you should be trying
out a solution by yourself. There are many alternate ways of doing it and you should explore them by yourself.
The below code works with Python 2.7
from __future__ import division
def convert_subject_data_to_student_data(subject_dict):
student_dict = {}
for k, v in subject_dict.items():
for k1, v1 in v.items():
if k1 not in student_dict:
student_dict[k1] = {k:v1}
else:
student_dict[k1][k] = v1
student_list = []
for k,v in student_dict.items():
st_dict = {}
st_dict['Name'] = k
st_dict['Average'] = sum(v.itervalues()) / len(v.keys())
st_dict.update(v)
student_list.append(st_dict)
print student_list
if __name__ == "__main__":
subject_dict = {
'Maths': dict(Mohsen=19, Sadegh=18, Hafez=15),
'Physics': dict(Sadegh=16, Hafez=17, Mohsen=17),
'Chemistry': dict(Hafez=13),
'Literature': dict(Sadegh=14),
'Biology': dict(Mohsen=16, Sadegh=10),
}
convert_subject_data_to_student_data(subject_dict)
sample_input = {
'Maths': dict(Mohsen=19, Sadegh=18, Hafez=15),
'Physics': dict(Sadegh=16, Hafez=17, Mohsen=17),
'Chemistry': dict(Hafez=13),
'Literature': dict(Sadegh=14),
'Biology': dict(Mohsen=16, Sadegh=10),
}
def foo(lessons):
result = {}
for lesson in lessons:
for user in lessons[lesson]:#dictionary
if result.get(user):
#print(result.get(user))
result.get(user).setdefault(lesson, lessons[lesson].get(user,0))
else:
result.setdefault(user, dict(name=user))
result.get(user).setdefault(lesson,lessons[lesson].get(user,0))
#return list(result.values())
return result.values()
#if name == '__main__':
print(foo(sample_input))
Related
im trying to add variables to a list that i created. Got a result from a session.execute.
i´ve done this:
def machine_id(session, machine_serial):
stmt_raw = '''
SELECT
id
FROM
machine
WHERE
machine.serial = :machine_serial_arg
'''
utc_now = datetime.datetime.utcnow()
utc_now_iso = pytz.utc.localize(utc_now).isoformat()
utc_start = datetime.datetime.utcnow() - datetime.timedelta(days = 30)
utc_start_iso = pytz.utc.localize(utc_start).isoformat()
stmt_args = {
'machine_serial_arg': machine_serial,
}
stmt = text(stmt_raw).columns(
#ts_insert = ISODateTime
)
result = session.execute(stmt, stmt_args)
ts = utc_now_iso
ts_start = utc_start_iso
ID = []
for row in result:
ID.append({
'id': row[0],
'ts': ts,
'ts_start': ts_start,
})
return ID
In trying to get the result over api like this:
def form_response(response, session):
result_machine_id = machine_id(session, machine_serial)
if not result_machine_id:
response['Error'] = 'Seriennummer nicht vorhanden/gefunden'
return
response['id_timerange'] = result_machine_id
Output looks fine.
{
"id_timerange": [
{
"id": 1,
"ts": "2020-08-13T08:32:25.835055+00:00",
"ts_start": "2020-07-14T08:32:25.835089+00:00"
}
]
}
Now i only want the id from it as a parameter for another function. Problem is i think its not a list. I cant select the first element. result_machine_id[0] result is like the posted Output. I think in my first function i only add ts & ts_start to the first row? Is it possible to add emtpy rows and then add 'ts':ts as value?
Help would be nice
If I have understood your question correctly ...
Your output looks like dict. so access its id_timerange key which gives you a list. Access the first element which gives you another dict. On this dict you have an id key:
result_machine_id["id_timerange"][0]["id"]
kanji = ['上','下','大','工','八','入','山','口','九','一','人','力','川','七','十','三','二','女',]
reading = ['じょう','か','たい','こう','はち','にゅう','さん','こう','く','いち','にん','りょく','かわ','しち','じゅう','さん','に','じょ']
definition = ['above','below','big','construction','eight','enter','mountain','mouth','nine','one','person','power','river','seven','ten','three','two','woman']
score = number_of_questions = kanji_item = 0
def question_format(prompt_type,lang,solution_selection):
global reading,definition,score,num_of_questions,kanji_item
question_prompt = 'What is the '+str(prompt_type)+' for "'+str(kanji[kanji_item])+'"? (Keyboard:'+str(lang)+')\n'
solution_selection = [reading,definition]
usr = input(question_prompt)
if usr in solution_selection[kanji_item] and kanji[kanji_item]:
score += 1
num_of_questions += 1
else:
pass
kanji_item += 1
while number_of_questions != 18:
question_format('READING','Japanese',[0])
print('You got ',score,'/',number_of_questions)
while number_of_questions != 36:
question_format('DEFINITION','English',[1])
print('You got ',score,'/',number_of_questions)
I can't get past 大. but I can't see where it's messing up. I've tried to change pretty much everything. "kanji_item" is supposed to give a common index number so that the answers can match up. It gets through the first two problems with no hassle, but for some reason refuses to accept my third problem.
Problems:
- wrong name using number_of_questions vs. num_of_questions
- wrong way to check truthyness if usr in solution_selection[kanji_item] and kanji[kanji_item]: - the last part is always True as it is a non empty string
- lots of globals wich is not considered very good style
It would be easier to zip your three list together so you get tuples of (kanji, reading, description) and feed 2 of those into your function depending on what you want to test. You do this 2 times, once for reading, once for description.
You can even randomize your list of tuples to get different "orders" in which questions are asked:
kanji = ['上', '下', '大', '工', '八', '入', '山', '口', '九', '一' , '人',
'力', '川', '七', '十', '三', '二', '女',]
reading = ['じょう', 'か', 'たい', 'こう', 'はち', 'にゅう', 'さん', 'こう', 'く',
'いち', 'にん', 'りょく', 'かわ', 'しち', 'じゅう', 'さん', 'に', 'じょ']
definition = ['above', 'below', 'big', 'construction', 'eight', 'enter', 'mountain',
'mouth', 'nine', 'one', 'person', 'power', 'river', 'seven', 'ten', 'three',
'two', 'woman']
import random
data = list(zip(kanji, reading, definition))
random.shuffle(data)
def question_format(prompt_type, lang, kanji, solution):
"""Creates a question about *kanji* - the correct answer is *solution*
Returns 1 if correct else 0."""
question_prompt = f'What is the {prompt_type} for {kanji}? (Keyboard: {lang})'
usr = input(question_prompt)
if usr == solution:
return 1
else:
return 0
questions_asked = 0
correct = 0
for (kanji, reading, _) in data:
correct += question_format('READING','Japanese', kanji, reading)
questions_asked += 1
print('You got ',correct,'/',questions_asked)
for (kanji, _, definition) in data:
correct += question_format('DEFINITION','ENGLISH', kanji, definition)
questions_asked += 1
print('You got ',correct,'/',questions_asked)
After zipping our list and shuffling them data looks like
[('山', 'さん', 'mountain'), ('女', 'じょ', 'woman'), ('力', 'りょく', 'power'),
('上', 'じょう', 'above'), ('九', 'く', 'nine'), ('川', 'かわ', 'river'),
('入', 'にゅう', 'enter'), ('三', 'さん', 'three'), ('口', 'こう', 'mouth'),
('二', 'に', 'two'), ('人', 'にん', 'person'), ('七', 'しち', 'seven'),
('一', 'いち', 'one'), ('工', 'こう', 'construction'), ('下', 'か', 'below'),
('八', 'はち', 'eight'), ('十', 'じゅう', 'ten'), ('大', 'たい', 'big')]
I have a use case where I have multiple line plots (with legends), and I need to update the line plots based on a column condition. Below is an example of two data set, based on the country, the column data source changes. But the issue I am facing is, the number of columns is not fixed for the data source, and even the types can vary. So, when I update the data source based on a callback when there is a new country selected, I get this error:
Error: attempted to retrieve property array for nonexistent field 'pay_conv_7d.content'.
I am guessing because in the new data source, the pay_conv_7d.content column doesn't exist, but in my plot those lines were already there. I have been trying to fix this issue by various means (making common columns for all country selection - adding the missing column in the data source in callback, but still get issues.
Is there any clean way to have multiple line plots updating using callback, and not do a lot of hackish way? Any insights or help would be really appreciated. Thanks much in advance! :)
def setup_multiline_plots(x_axis, y_axis, title_text, data_source, plot):
num_categories = len(data_source.data['categories'])
legends_list = list(data_source.data['categories'])
colors_list = Spectral11[0:num_categories]
# xs = [data_source.data['%s.'%x_axis].values] * num_categories
# ys = [data_source.data[('%s.%s')%(y_axis,column)] for column in data_source.data['categories']]
# data_source.data['x_series'] = xs
# data_source.data['y_series'] = ys
# plot.multi_line('x_series', 'y_series', line_color=colors_list,legend='categories', line_width=3, source=data_source)
plot_list = []
for (colr, leg, column) in zip(colors_list, legends_list, data_source.data['categories']):
xs, ys = '%s.'%x_axis, ('%s.%s')%(y_axis,column)
plot.line(xs,ys, source=data_source, color=colr, legend=leg, line_width=3, name=ys)
plot_list.append(ys)
data_source.data['plot_names'] = data_source.data.get('plot_names',[]) + plot_list
plot.title.text = title_text
def update_plot(country, timeseries_df, timeseries_source,
aggregate_df, aggregate_source, category,
plot_pay_7d, plot_r_pay_90d):
aggregate_metrics = aggregate_df.loc[aggregate_df.country == country]
aggregate_metrics = aggregate_metrics.nlargest(10, 'cost')
category_types = list(aggregate_metrics[category].unique())
timeseries_df = timeseries_df[timeseries_df[category].isin(category_types)]
timeseries_multi_line_metrics = get_multiline_column_datasource(timeseries_df, category, country)
# len_series = len(timeseries_multi_line_metrics.data['time.'])
# previous_legends = timeseries_source.data['plot_names']
# current_legends = timeseries_multi_line_metrics.data.keys()
# common_legends = list(set(previous_legends) & set(current_legends))
# additional_legends_list = list(set(previous_legends) - set(current_legends))
# for legend in additional_legends_list:
# zeros = pd.Series(np.array([0] * len_series), name=legend)
# timeseries_multi_line_metrics.add(zeros, legend)
# timeseries_multi_line_metrics.data['plot_names'] = previous_legends
timeseries_source.data = timeseries_multi_line_metrics.data
aggregate_source.data = aggregate_source.from_df(aggregate_metrics)
def get_multiline_column_datasource(df, category, country):
df_country = df[df.country == country]
df_pivoted = pd.DataFrame(df_country.pivot_table(index='time', columns=category, aggfunc=np.sum).reset_index())
df_pivoted.columns = df_pivoted.columns.to_series().str.join('.')
categories = list(set([column.split('.')[1] for column in list(df_pivoted.columns)]))[1:]
data_source = ColumnDataSource(df_pivoted)
data_source.data['categories'] = categories
Recently I had to update data on a Multiline glyph. Check my question if you want to take a look at my algorithm.
I think you can update a ColumnDataSource in three ways at least:
You can create a dataframe to instantiate a new CDS
cds = ColumnDataSource(df_pivoted)
data_source.data = cds.data
You can create a dictionary and assign it to the data attribute directly
d = {
'xs0': [[7.0, 986.0], [17.0, 6.0], [7.0, 67.0]],
'ys0': [[79.0, 69.0], [179.0, 169.0], [729.0, 69.0]],
'xs1': [[17.0, 166.0], [17.0, 116.0], [17.0, 126.0]],
'ys1': [[179.0, 169.0], [179.0, 1169.0], [1729.0, 169.0]],
'xs2': [[27.0, 276.0], [27.0, 216.0], [27.0, 226.0]],
'ys2': [[279.0, 269.0], [279.0, 2619.0], [2579.0, 2569.0]]
}
data_source.data = d
Here if you need different sizes of columns or empty columns you can fill the gaps with NaN values in order to keep column sizes. And I think this is the solution to your question:
import numpy as np
d = {
'xs0': [[7.0, 986.0], [17.0, 6.0], [7.0, 67.0]],
'ys0': [[79.0, 69.0], [179.0, 169.0], [729.0, 69.0]],
'xs1': [[17.0, 166.0], [np.nan], [np.nan]],
'ys1': [[179.0, 169.0], [np.nan], [np.nan]],
'xs2': [[np.nan], [np.nan], [np.nan]],
'ys2': [[np.nan], [np.nan], [np.nan]]
}
data_source.data = d
Or if you only need to modify a few values then you can use the method patch. Check the documentation here.
The following example shows how to patch entire column elements. In this case,
source = ColumnDataSource(data=dict(foo=[10, 20, 30], bar=[100, 200, 300]))
patches = {
'foo' : [ (slice(2), [11, 12]) ],
'bar' : [ (0, 101), (2, 301) ],
}
source.patch(patches)
After this operation, the value of the source.data will be:
dict(foo=[11, 22, 30], bar=[101, 200, 301])
NOTE: It is important to make the update in one go to avoid performance issues
Could you help me wiht my issue ? Let's say that I have few list with ID's their members, like below:
team_A = [1,2,3,4,5]
team_B = [6,7,8,9,10]
team_C = [11,12,13,14,15]
and now I have a dictionary with their values:
dictionary = {5:23, 10:68, 15:68, 4:1, 9:37, 14:21, 3:987, 8:3, 13:14, 2:98, 7:74, 12:47, 1:37, 6:82, 11:99}
I would like to take correct elements from dictionary and create new dictionary for team A, B and C, like below:
team_A_values = {5:23, 4:1, 3:987, 2:98, 1:37}
Could you give advice how to do that ? Thanks for your help
You can do something like below by just Iterating through the lists
team_A = [1,2,3,4,5]
team_B = [6,7,8,9,10]
team_C = [11,12,13,14,15]
dictionary = {5:23, 10:68, 15:68, 4:1, 9:37, 14:21, 3:987, 8:3, 13:14, 2:98, 7:74, 12:47, 1:37, 6:82, 11:99}
team_A_values = {}
for i in team_A:
team_A_values[i] = dictionary[i]
print(team_A_values )
can repeat this to team B and team C
in that case you can do like this
team_values = [{i: dictionary[i] for i in team_A },{i: dictionary[i] for i in team_B},{i: dictionary[i] for i in team_C}]
teamA,teamB,teamC = team_values
print(team_values)
print(teamA)
print(teamB)
print(teamC)
in one line you can do like this
team_values = [{i: dictionary[i] for i in team } for team in [team_A ,team_B ,team_C]]
teamA,teamB,teamC = team_values
print(team_values)
print(teamA)
print(teamB)
print(teamC)
I'm not sure if the title accurately describes what I'm trying to do. I have a Python3.x script that I wrote that will issue flood warning to my facebook page when the river near my home has reached it's lowest flood stage. Right now the script works, however it only reports data from one measuring station. I would like to be able to process the data from all of the stations in my county (total of 5), so I was thinking that maybe a class method may do the trick but I'm not sure how to implement it. I've been teaching myself Python since January and feel pretty comfortable with the language for the most part, and while I have a good idea of how to build a class object I'm not sure how my flow chart should look. Here is the code now:
#!/usr/bin/env python3
'''
Facebook Flood Warning Alert System - this script will post a notification to
to Facebook whenever the Sabine River # Hawkins reaches flood stage (22.3')
'''
import requests
import facebook
from lxml import html
graph = facebook.GraphAPI(access_token='My_Access_Token')
river_url = 'http://water.weather.gov/ahps2/river.php?wfo=SHV&wfoid=18715&riverid=203413&pt%5B%5D=147710&allpoints=143204%2C147710%2C141425%2C144668%2C141750%2C141658%2C141942%2C143491%2C144810%2C143165%2C145368&data%5B%5D=obs'
ref_url = 'http://water.weather.gov/ahps2/river.php?wfo=SHV&wfoid=18715&riverid=203413&pt%5B%5D=147710&allpoints=143204%2C147710%2C141425%2C144668%2C141750%2C141658%2C141942%2C143491%2C144810%2C143165%2C145368&data%5B%5D=all'
def checkflood():
r = requests.get(river_url)
tree = html.fromstring(r.content)
stage = ''.join(tree.xpath('//div[#class="stage_stage_flow"]//text()'))
warn = ''.join(tree.xpath('//div[#class="current_warns_statmnts_ads"]/text()'))
stage_l = stage.split()
level = float(stage_l[2])
#check if we're at flood level
if level < 22.5:
pass
elif level == 37:
major_diff = level - 23.0
major_r = ('The Sabine River near Hawkins, Tx has reached [Major Flood Stage]: #', stage_l[2], 'Ft. ', str(round(major_diff, 2)), ' Ft. \n Please click the link for more information.\n\n Current Warnings and Alerts:\n ', warn)
major_p = ''.join(major_r)
graph.put_object(parent_object='me', connection_name='feed', message = major_p, link = ref_url)
<--snip-->
checkflood()
Each station has different 5 different catagories for flood stage: Action, Flood, Moderate, Major, each different depths per station. So for Sabine river in Hawkins it will be Action - 22', Flood - 24', Moderate - 28', Major - 32'. For the other statinos those depths are different. So I know that I'll have to start out with something like:
class River:
def __init__(self, id, stage):
self.id = id #station ID
self.stage = stage #river level'
#staticmethod
def check_flood(stage):
if stage < 22.5:
pass
elif stage.....
but from there I'm not sure what to do. Where should it be added in(to?) the code, should I write a class to handle the Facebook postings as well, is this even something that needs a class method to handle, is there any way to clean this up for efficiency? I'm not looking for anyone to write this up for me, but some tips and pointers would sure be helpful. Thanks everyone!
EDIT Here is what I figured out and is working:
class River:
name = ""
stage = ""
action = ""
flood = ""
mod = ""
major = ""
warn = ""
def checkflood(self):
if float(self.stage) < float(self.action):
pass
elif float(self.stage) >= float(self.major):
<--snip-->
mineola = River()
mineola.name = stations[0]
mineola.stage = stages[0]
mineola.action = "13.5"
mineola.flood = "14.0"
mineola.mod = "18.0"
mineola.major = "21.0"
mineola.alert = warn[0]
hawkins = River()
hawkins.name = stations[1]
hawkins.stage = stages[1]
hawkins.action = "22.5"
hawkins.flood = "23.0"
hawkins.mod = "32.0"
hawkins.major = "37.0"
hawkins.alert = warn[1]
<--snip-->
So from here I'm tring to stick all the individual river blocks into one block. What I have tried so far is this:
class River:
... name = ""
... stage = ""
... def testcheck(self):
... return self.name, self.stage
...
>>> for n in range(num_river):
... stations[n] = River()
... stations[n].name = stations[n]
... stations[n].stage = stages[n]
...
>>> for n in range(num_river):
... stations[n].testcheck()
...
<__main__.River object at 0x7fbea469bc50> 4.13
<__main__.River object at 0x7fbea46b4748> 20.76
<__main__.River object at 0x7fbea46b4320> 22.13
<__main__.River object at 0x7fbea46b4898> 16.08
So this doesn't give me the printed results that I was expecting. How can I return the string instead of the object? Will I be able to define the Class variables in this manner or will I have to list them out individually? Thanks again!
After reading many, many, many articles and tutorials on class objects I was able to come up with a solution for creating the objects using list elements.
class River():
def __init__(self, river, stage, flood, action):
self.river = river
self.stage = stage
self.action = action
self.flood = flood
self.action = action
def alerts(self):
if float(self.stage < self.flood):
#alert = "The %s is below Flood Stage (%sFt) # %s Ft. \n" % (self.river, self.flood, self.stage)
pass
elif float(self.stage > self.flood):
alert = "The %s has reached Flood Stage(%sFt) # %sFt. Warnings: %s \n" % (self.river, self.flood, self.stage, self.action)
return alert
'''this is the function that I was trying to create
to build the class objects automagically'''
def riverlist():
river_list = []
for n in range(len(rivers)):
station = River(river[n], stages[n], floods[n], warns[n])
river_list.append(station)
return river_list
if __name__ == '__main__':
for x in riverlist():
print(x.alerts())