I need to extract a tuple from two column values
def selectiem():
item = table.selection()
a, b= [], []
for i in item:
a.append(table.item(i)['values'][22])
b.append(table.item(i)['values'][23])
print(a, b)
result of print: ['44.38', '44.4', '44.13'] ['40.38', '30.4', '29.13']
I tried to extract like this:
print(a[1], b[1], a[2], b[2]) # but how to do this for all the selected items?
My expectation are for a tuples of this form:
expectation = [44.38, 40.38], [44.4, 30.4], [44.13, 29.13]
Related
I need to find the arithmetic mean of each columns by returning res?
def ave(df, name):
df = {
'Courses':["Spark","PySpark","Python","pandas",None],
'Fee' :[20000,25000,22000,None,30000],
'Duration':['30days','40days','35days','None','50days'],
'Discount':[1000,2300,1200,2000,None]}
#CODE HERE
res = []
for i in df.columns:
res.append(col_ave(df, i))
I tried individually creating codes for the mean but Im having trouble
I have an excel file with the following data:
LogID
T-1111
P-09899
P-09189,T-0011
T-111,T-2111
P-09099,P-7897
RCT-0989,RCT-099
I need to extract the first column LogID before the delimiter "-" and then populate a second column 'LogType' based on the string extracted (T is Tank LogType, P is Pump LogType)
For the above input, the output should be
LogID
LogType
T-1111
Tank
P-09899
Pump
P-09189,T-0011
Multiple
T-111,T-2111
Tank
P-09099,P-7897
Pump
RCT-0989,RCT-099
Reactor
I have written a function to do this in python:
def log_parser(log_string):
log_dict = { "T":"Tank","P":"Pump" }
log_list = log_string.split(",")
for i in log_list:
str_extract = i.upper().split("-",1)
if len(log_list) ==1:
result = log_dict[str_extract[0]]
return result
break
else:
idx = log_list.index(i)
for j in range(len(log_list)):
if (idx == j):
continue
str_extract_j = log_list[j].upper().split("-",1)
if str_extract_j[0] != str_extract[0]:
result = "Multiple"
return result
break
else:
result = log_dict[str_extract[0]]
return result
I am not sure how to implement this function in pandas..
Can i define the function in pandas and then use the lamba apply funtion like this:
test_df['LogType'] = test_df[['LogID']].apply(lambda x:log_parser(x), axis=1)
You can use:
# mapping dictionary for types
d = {'T': 'Tank', 'P': 'Pump'}
# extract letters before -
s = df['LogID'].str.extractall('([A-Z])-')[0]
# group by index
g = s.groupby(level=0)
df['LogType'] = (g.first() # get first match
.map(d) # map type name
# mask if several types
.mask(g.nunique().gt(1),
'Multiple')
)
Output:
LogID LogType
0 T-1111 Tank
1 P-09899 Pump
2 P-09189,T-0011 Multiple
I am new to Hypothesis and I would like to know if there is a better way to use to Hypothesis than what I have done here...
class TestFindEmptyColumns:
def test_one_empty_column(self):
input = pd.DataFrame({
'quantity': [None],
})
expected_output = ['quantity']
assert find_empty_columns(input) == expected_output
def test_no_empty_column(self):
input = pd.DataFrame({
'item': ["Item1", ],
'quantity': [10, ],
})
expected_output = []
assert find_empty_columns(input) == expected_output
#given(data_frames([
column(name='col1', elements=st.none() | st.integers()),
column(name='col2', elements=st.none() | st.integers()),
]))
def test_dataframe_with_random_number_of_columns(self, df):
df_with_no_empty_columns = df.dropna(how='all', axis=1)
result = find_empty_columns(df)
# None of the empty columns should be in the reference dataframe df_with_no_empty_columns
assert set(result).isdisjoint(df_with_no_empty_columns.columns)
# The above assert does not catch the condition if the result is a column name
# that is not there in the data-frame at all e.g. 'col3'
assert set(result).issubset(df.columns)
Ideally, I want a dataframe which has a variable number of columns in each test run. The columns can contain any value - some of the columns should contains all null values. Any help would be appreciated?
I have a function that returns the BMI from a given dataframe with columns 'Weight' and 'Height'
Here is the function:
def BMI(dataframe):
return dataframe['Weight'] / (dataframe['Height']**2)
I added new column 'Height In Meters' to the dataframe 'data' with:
data['Height In Meters'] = data['Height']/100
What i would like to do next, is to apply the original function on the dataframe 'data',
but instead of using the column 'Height', the calculation would be by using the new column 'Height In Meters'.
the result should be a new column called 'BMI' in the dataframe 'data', that shows for each row the calculation using 'Height In Meters'.
I tried:
data['BMI'] = data[['Weight','Height In Meters']].apply(BMI,axis=1)
But that doesn't seem to work.
You could pass the column names as arguments:
def BMI(dataframe, col1, col2):
return dataframe[col1] / (dataframe[col2]**2)
a = data.apply(BMI, args=('Weight', 'Height'), axis=1)
data['Height In Meters'] = data['Height']/100
b = data.apply(BMI, args=('Weight', 'Height In Meters'), axis=1)
I have a numpy array, a:
a = np.array([[-21.78878256, 97.37484004, -11.54228119],
[ -5.72592375, 99.04189958, 3.22814204],
[-19.80795922, 95.99377136, -10.64537733]])
I have another array, b:
b = np.array([[ 54.64642121, 64.5172014, 44.39991983],
[ 9.62420892, 95.14361441, 0.67014312],
[ 49.55036427, 66.25136632, 40.38778238]])
I want to extract minimum value indices from the array, b.
ixs = [[2],
[2],
[2]]
Then, want to extract elements from the array, a using the indices, ixs:
The expected answer is:
result = [[-11.54228119]
[3.22814204]
[-10.64537733]]
I tried as:
ixs = np.argmin(b, axis=1)
print ixs
[2,2,2]
result = np.take(a, ixs)
print result
Nope!
Any ideas are welcomed
You can use
result = a[np.arange(a.shape[0]), ixs]
np.arange will generate indices for each row and ixs will have indices for each column. So effectively result will have required result.
You can try using below code
np.take(a, ixs, axis = 1)[:,0]
The initial section will create a 3 by 3 array and slice the first column
>>> np.take(a, ixs, axis = 1)
array([[-11.54228119, -11.54228119, -11.54228119],
[ 3.22814204, 3.22814204, 3.22814204],
[-10.64537733, -10.64537733, -10.64537733]])