In [57]: # importing pandas library and data file in csv format

In [58]: import pandas as pd

In [59]: df = pd.read_csv("DATA1.csv",skiprows=1)
df

Out[59]: Building Monday Tuesday Wednesday Thursday Friday Saturday Sunday

0 A 91.0 95.0 97.0 99.0 90.0 95.0 54.0

1 B 234.0 281.0 293.0 280.0 269.0 165.0 34.0

2 C 156.0 149.0 174.0 167.0 146.0 61.0 8.0

3 D 81.0 120.0 110.0 91.0 95.0 68.0 8.0

4 E 252.0 231.0 287.0 259.0 273.0 226.0 6.0

5 F 97.0 117.0 134.0 117.0 118.0 74.0 1.0

6 G 21.0 21.0 21.0 21.0 21.0 21.0 0.0

7 H 7.0 8.0 7.0 7.0 7.0 8.0 4.0

8 I 62.0 56.0 48.0 42.0 42.0 44.0 0.0

9 J 2.0 0.0 0.0 2.0 2.0 0.0 0.0

10 K 23.0 38.0 30.0 27.0 25.0 15.0 0.0

11 L 4.0 3.0 0.0 0.0 0.0 0.0 0.0

12 M 14.0 24.0 19.0 29.0 23.0 14.0 18.0

13 NaN NaN NaN NaN NaN NaN NaN NaN

14 waste collected or not collected : collected (... NaN NaN NaN NaN NaN NaN NaN

15 A 1.0 1.0 1.0 1.0 1.0 1.0 0.0

16 B 1.0 1.0 1.0 1.0 1.0 1.0 0.0

17 C 1.0 1.0 1.0 1.0 1.0 1.0 0.0

18 D 1.0 1.0 1.0 1.0 1.0 1.0 0.0

19 E 1.0 1.0 1.0 1.0 1.0 1.0 0.0

20 F 0.0 0.0 1.0 1.0 1.0 1.0 0.0

21 G 0.0 0.0 0.0 0.0 0.0 0.0 0.0

22 H 0.0 0.0 0.0 0.0 0.0 0.0 0.0

23 I 1.0 0.0 0.0 0.0 0.0 0.0 0.0

24 J 0.0 0.0 0.0 0.0 0.0 0.0 0.0

25 K 0.0 0.0 0.0 0.0 0.0 0.0 0.0

26 L 0.0 0.0 0.0 0.0 0.0 0.0 0.0

27 M 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [60]: # rearranging the data

In [61]: class_schedule = df.iloc[0:13]

class_schedule.set_index('Building',inplace=True)
class_schedule

Out[61]: Monday Tuesday Wednesday Thursday Friday Saturday Sunday

Building

A 91.0 95.0 97.0 99.0 90.0 95.0 54.0

B 234.0 281.0 293.0 280.0 269.0 165.0 34.0

C 156.0 149.0 174.0 167.0 146.0 61.0 8.0

D 81.0 120.0 110.0 91.0 95.0 68.0 8.0

E 252.0 231.0 287.0 259.0 273.0 226.0 6.0

F 97.0 117.0 134.0 117.0 118.0 74.0 1.0

G 21.0 21.0 21.0 21.0 21.0 21.0 0.0

H 7.0 8.0 7.0 7.0 7.0 8.0 4.0

I 62.0 56.0 48.0 42.0 42.0 44.0 0.0

J 2.0 0.0 0.0 2.0 2.0 0.0 0.0

K 23.0 38.0 30.0 27.0 25.0 15.0 0.0

L 4.0 3.0 0.0 0.0 0.0 0.0 0.0

M 14.0 24.0 19.0 29.0 23.0 14.0 18.0

In [62]: waste_info = df.iloc[15:28]

waste_info.set_index("Building",inplace=True)
waste_info

Out[62]: Monday Tuesday Wednesday Thursday Friday Saturday Sunday

Building

A 1.0 1.0 1.0 1.0 1.0 1.0 0.0

B 1.0 1.0 1.0 1.0 1.0 1.0 0.0

C 1.0 1.0 1.0 1.0 1.0 1.0 0.0

D 1.0 1.0 1.0 1.0 1.0 1.0 0.0

E 1.0 1.0 1.0 1.0 1.0 1.0 0.0

F 0.0 0.0 1.0 1.0 1.0 1.0 0.0

G 0.0 0.0 0.0 0.0 0.0 0.0 0.0

H 0.0 0.0 0.0 0.0 0.0 0.0 0.0

I 1.0 0.0 0.0 0.0 0.0 0.0 0.0

J 0.0 0.0 0.0 0.0 0.0 0.0 0.0

K 0.0 0.0 0.0 0.0 0.0 0.0 0.0

L 0.0 0.0 0.0 0.0 0.0 0.0 0.0

M 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [63]: # creating a new dataframe with new set of columns

In [64]: days = list(class_schedule.columns)

buildings = list(class_schedule.index)
print(days,buildings)

['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday'] ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M']

In [65]: new_cols = days + buildings + ["classes","waste_collected"]

new_cols

Out[65]: ['Monday',
'Tuesday',
'Wednesday',
'Thursday',
'Friday',
'Saturday',
'Sunday',
'A',
'B',
'C',
'D',
'E',
'F',
'G',
'H',
'I',
'J',
'K',
'L',
'M',
'classes',
'waste_collected']

In [66]: new_df = pd.DataFrame(columns=new_cols)

new_df

Out[66]: Monday Tuesday Wednesday Thursday Friday Saturday Sunday A B C ... F G H I J K L M classes waste_collected

0 rows × 22 columns

In [67]: # 'one hot encoding' for assigning numeric values to string or character inputs

In [68]: for day in days:

for building in buildings:
row=[0]*22
dI = new_cols.index(day)
row[dI] = 1
bI = new_cols.index(building)
row[bI] = 1
row[-2] = class_schedule[day][building]
row[-1] = waste_info[day][building]
series_row = pd.Series(row, index=new_df.columns )
new_df = new_df.append(series_row,ignore_index=True)
new_df

Out[68]: Monday Tuesday Wednesday Thursday Friday Saturday Sunday A B C ... F G H I J K L M classes waste_collected

0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 91.0 1.0

1 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 234.0 1.0

2 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 156.0 1.0

3 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 81.0 1.0

4 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 252.0 1.0

... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

86 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0

87 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0

88 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0

89 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0

90 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 18.0 0.0

91 rows × 22 columns

In [69]: # performing Logistic Regression with ScikitLearn

In [70]: from sklearn.linear_model import LogisticRegressionCV

In [71]: # taking 'waste_collected' as 'y' i.e the dependent variable (to be predicted) and all other columns as the independent variable 'x.'

In [72]: y = new_df['waste_collected']
X = new_df.drop(['waste_collected'],axis=1)

In [73]: my_model = LogisticRegressionCV(cv=5, random_state=0).fit(X, y)

result = my_model.predict_proba(X)

C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):

STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\tapin\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(

In [74]: # no. of classes into which the output is classified and their probabilities

In [75]: print(my_model.classes_)
result

[0. 1.]
Out[75]: array([[1.57815565e-01, 8.42184435e-01],
[3.18800532e-06, 9.99996812e-01],
[1.26868415e-03, 9.98731316e-01],
[2.86993656e-01, 7.13006344e-01],
[7.99583728e-07, 9.99999200e-01],
[1.06798461e-01, 8.93201539e-01],
[9.76032728e-01, 2.39672721e-02],
[9.91688138e-01, 8.31186239e-03],
[6.35804123e-01, 3.64195877e-01],
[9.94323294e-01, 5.67670566e-03],
[9.72179252e-01, 2.78207480e-02],
[9.93386831e-01, 6.61316874e-03],
[9.85862147e-01, 1.41378533e-02],
[1.21987791e-01, 8.78012209e-01],
[8.69018382e-08, 9.99999913e-01],
[2.18780436e-03, 9.97812196e-01],
[1.98820681e-02, 9.80117932e-01],
[4.04561838e-06, 9.99995954e-01],
[2.52800024e-02, 9.74719998e-01],
[9.76221656e-01, 2.37783441e-02],
[9.91102201e-01, 8.89779874e-03],
[7.36182182e-01, 2.63817818e-01],
[9.95166967e-01, 4.83303258e-03],
[9.17555227e-01, 8.24447728e-02],
[9.93922003e-01, 6.07799708e-03],
[9.70245840e-01, 2.97541595e-02],
[1.05820160e-01, 8.94179840e-01],
[3.43349987e-08, 9.99999966e-01],
[3.19024161e-04, 9.99680976e-01],
[4.16282878e-02, 9.58371712e-01],
[5.44212012e-08, 9.99999946e-01],
[6.93066679e-03, 9.93069333e-01],
[9.76063558e-01, 2.39364425e-02],
[9.91699001e-01, 8.30099938e-03],
[8.36714156e-01, 1.63285844e-01],
[9.95134206e-01, 4.86579448e-03],
[9.53351615e-01, 4.66483851e-02],
[9.95134222e-01, 4.86577785e-03],
[9.79404772e-01, 2.05952283e-02],
[9.20581516e-02, 9.07941848e-01],
[9.31166202e-08, 9.99999907e-01],
[5.45561274e-04, 9.99454439e-01],
[1.57379628e-01, 8.42620372e-01],
[4.67183667e-07, 9.99999533e-01],
[2.50898522e-02, 9.74910148e-01],
[9.76041201e-01, 2.39587990e-02],
[9.91691123e-01, 8.30887680e-03],
[8.90312425e-01, 1.09687575e-01],
[9.94325339e-01, 5.67466119e-03],
[9.62559588e-01, 3.74404117e-02],
[9.95129589e-01, 4.87041134e-03],
[9.56592342e-01, 4.34076584e-02],
[1.68295711e-01, 8.31704289e-01],
[2.16696040e-07, 9.99999783e-01],
[2.73109190e-03, 9.97268908e-01],
[1.20734381e-01, 8.79265619e-01],
[1.59317110e-07, 9.99999841e-01],
[2.32695744e-02, 9.76730426e-01],
[9.76032702e-01, 2.39672984e-02],
[9.91688128e-01, 8.31187163e-03],
[8.90276933e-01, 1.09723067e-01],
[9.94323288e-01, 5.67671198e-03],
[9.67708269e-01, 3.22917311e-02],
[9.95127827e-01, 4.87217291e-03],
[9.72166606e-01, 2.78333943e-02],
[1.20231749e-01, 8.79768251e-01],
[6.33252930e-04, 9.99366747e-01],
[6.50420307e-01, 3.49579693e-01],
[5.20045116e-01, 4.79954884e-01],
[5.84290789e-06, 9.99994157e-01],
[4.09646391e-01, 5.90353609e-01],
[9.75835668e-01, 2.41643318e-02],
[9.90955528e-01, 9.04447231e-03],
[8.73420462e-01, 1.26579538e-01],
[9.95086966e-01, 4.91303367e-03],
[9.84631053e-01, 1.53689471e-02],
[9.95086983e-01, 4.91301687e-03],
[9.85744725e-01, 1.42552755e-02],
[7.63255733e-01, 2.36744267e-01],
[9.37645265e-01, 6.23547353e-02],
[9.91018466e-01, 8.98153396e-03],
[9.90992328e-01, 9.00767225e-03],
[9.92317771e-01, 7.68222921e-03],
[9.94798656e-01, 5.20134415e-03],
[9.95145057e-01, 4.85494283e-03],
[9.93406604e-01, 6.59339645e-03],
[9.95144870e-01, 4.85512957e-03],
[9.95141809e-01, 4.85819143e-03],
[9.95147901e-01, 4.85209900e-03],
[9.95141825e-01, 4.85817482e-03],
[9.80927963e-01, 1.90720373e-02]])

In [76]: # printing the probability output in the tabular form

In [77]: waste_not_collected = pd.DataFrame(columns = ['Day','A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M'])
waste_collected = pd.DataFrame(columns = ['Day','A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M'])
i=0
for day in days:
row_nc = []
row_c = []
row_nc.append(day)
row_c.append(day)
for building in buildings:
i+=1
row_nc.append(round(result[i-1][0],3))
row_c.append(round(result[i-1][1],3))
series_nc = pd.Series(row_nc, index=waste_not_collected.columns )
waste_not_collected = waste_not_collected.append(series_nc,ignore_index=True)
series_c = pd.Series(row_c, index=waste_collected.columns )
waste_collected = waste_collected.append(series_c,ignore_index=True)

In [78]: waste_not_collected

Out[78]: Day A B C D E F G H I J K L M

0 Monday 0.158 0.000 0.001 0.287 0.000 0.107 0.976 0.992 0.636 0.994 0.972 0.993 0.986

1 Tuesday 0.122 0.000 0.002 0.020 0.000 0.025 0.976 0.991 0.736 0.995 0.918 0.994 0.970

2 Wednesday 0.106 0.000 0.000 0.042 0.000 0.007 0.976 0.992 0.837 0.995 0.953 0.995 0.979

3 Thursday 0.092 0.000 0.001 0.157 0.000 0.025 0.976 0.992 0.890 0.994 0.963 0.995 0.957

4 Friday 0.168 0.000 0.003 0.121 0.000 0.023 0.976 0.992 0.890 0.994 0.968 0.995 0.972

5 Saturday 0.120 0.001 0.650 0.520 0.000 0.410 0.976 0.991 0.873 0.995 0.985 0.995 0.986

6 Sunday 0.763 0.938 0.991 0.991 0.992 0.995 0.995 0.993 0.995 0.995 0.995 0.995 0.981

In [79]: waste_collected

Out[79]: Day A B C D E F G H I J K L M

0 Monday 0.842 1.000 0.999 0.713 1.000 0.893 0.024 0.008 0.364 0.006 0.028 0.007 0.014

1 Tuesday 0.878 1.000 0.998 0.980 1.000 0.975 0.024 0.009 0.264 0.005 0.082 0.006 0.030

2 Wednesday 0.894 1.000 1.000 0.958 1.000 0.993 0.024 0.008 0.163 0.005 0.047 0.005 0.021

3 Thursday 0.908 1.000 0.999 0.843 1.000 0.975 0.024 0.008 0.110 0.006 0.037 0.005 0.043

4 Friday 0.832 1.000 0.997 0.879 1.000 0.977 0.024 0.008 0.110 0.006 0.032 0.005 0.028

5 Saturday 0.880 0.999 0.350 0.480 1.000 0.590 0.024 0.009 0.127 0.005 0.015 0.005 0.014

6 Sunday 0.237 0.062 0.009 0.009 0.008 0.005 0.005 0.007 0.005 0.005 0.005 0.005 0.019

In [80]: # converting the output table into csv format and downloading

In [81]: waste_not_collected.to_csv("probability (waste not collected).csv",index=False)

In [82]: waste_collected.to_csv("probability (waste collected).csv",index=False)

In [83]: # predicted output

In [84]: pred_result = my_model.predict(X)

pred_result

Out[84]: array([1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1.,
1., 1., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 0., 0.,
0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0.,
0., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 1., 1., 0.,
0., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0.])

In [85]: actual_output = pd.DataFrame(columns = ['Day','A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M'])
i=0
for day in days:
row=[]
row.append(day)
for building in buildings:
i+=1
row.append(pred_result[i-1])
series_ao = pd.Series(row, index=actual_output.columns )
actual_output = actual_output.append(series_ao,ignore_index=True)
actual_output

Out[85]: Day A B C D E F G H I J K L M

0 Monday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

1 Tuesday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

2 Wednesday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

3 Thursday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

4 Friday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

5 Saturday 1.0 1.0 0.0 0.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

6 Sunday 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [86]: actual_output.to_csv("predictd result.csv",index=False)

In [87]: # classification report of the model which measures the quality of predictions

In [88]: from sklearn.metrics import classification_report

report=classification_report(y,pred_result)
print(report)

precision recall f1-score support

0.0 0.95 0.96 0.96 56

1.0 0.94 0.91 0.93 35

accuracy 0.95 91
macro avg 0.94 0.94 0.94 91
weighted avg 0.94 0.95 0.94 91

In [89]: # plotting the Receiver Operating Curve (ROC Curve)

In [90]: from sklearn.metrics import roc_auc_score

from sklearn.metrics import roc_curve,auc
required_curve=roc_auc_score(y,pred_result)
fpr,tpr,thresholds=roc_curve(y,pred_result,pos_label=1)

In [91]: import matplotlib.pyplot as plt

plt.figure()
plt.plot(fpr,tpr,color='darkorange',lw=1,label='ROC curve(area = %0.2f)'% required_curve)
plt.plot([0, 1], [0, 1], color='navy', lw=1, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.0])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic Curve')
plt.legend(loc="lower right")
plt.show()

In [92]: actual_output=actual_output.set_index(['Day'])
actual_output

Out[92]: A B C D E F G H I J K L M

Day

Monday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Tuesday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Wednesday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Thursday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Friday 1.0 1.0 1.0 1.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Saturday 1.0 1.0 0.0 0.0 1.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Sunday 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [93]: actual_output=actual_output.transpose()
actual_output

Out[93]: Day Monday Tuesday Wednesday Thursday Friday Saturday Sunday

A 1.0 1.0 1.0 1.0 1.0 1.0 0.0

B 1.0 1.0 1.0 1.0 1.0 1.0 0.0

C 1.0 1.0 1.0 1.0 1.0 0.0 0.0

D 1.0 1.0 1.0 1.0 1.0 0.0 0.0

E 1.0 1.0 1.0 1.0 1.0 1.0 0.0

F 1.0 1.0 1.0 1.0 1.0 1.0 0.0

G 0.0 0.0 0.0 0.0 0.0 0.0 0.0

H 0.0 0.0 0.0 0.0 0.0 0.0 0.0

I 0.0 0.0 0.0 0.0 0.0 0.0 0.0

J 0.0 0.0 0.0 0.0 0.0 0.0 0.0

K 0.0 0.0 0.0 0.0 0.0 0.0 0.0

L 0.0 0.0 0.0 0.0 0.0 0.0 0.0

M 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [94]: actual_output.insert(0,'Buildings',['A','B','C','D','E','F','G','H','I','J','K','L','M'],True)
actual_output

Out[94]: Day Buildings Monday Tuesday Wednesday Thursday Friday Saturday Sunday

A A 1.0 1.0 1.0 1.0 1.0 1.0 0.0

B B 1.0 1.0 1.0 1.0 1.0 1.0 0.0

C C 1.0 1.0 1.0 1.0 1.0 0.0 0.0

D D 1.0 1.0 1.0 1.0 1.0 0.0 0.0

E E 1.0 1.0 1.0 1.0 1.0 1.0 0.0

F F 1.0 1.0 1.0 1.0 1.0 1.0 0.0

G G 0.0 0.0 0.0 0.0 0.0 0.0 0.0

H H 0.0 0.0 0.0 0.0 0.0 0.0 0.0

I I 0.0 0.0 0.0 0.0 0.0 0.0 0.0

J J 0.0 0.0 0.0 0.0 0.0 0.0 0.0

K K 0.0 0.0 0.0 0.0 0.0 0.0 0.0

L L 0.0 0.0 0.0 0.0 0.0 0.0 0.0

M M 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [95]: actual_output=actual_output.set_index(['Buildings'])
actual_output

Out[95]: Day Monday Tuesday Wednesday Thursday Friday Saturday Sunday

Buildings

A 1.0 1.0 1.0 1.0 1.0 1.0 0.0

B 1.0 1.0 1.0 1.0 1.0 1.0 0.0

C 1.0 1.0 1.0 1.0 1.0 0.0 0.0

D 1.0 1.0 1.0 1.0 1.0 0.0 0.0

E 1.0 1.0 1.0 1.0 1.0 1.0 0.0

F 1.0 1.0 1.0 1.0 1.0 1.0 0.0

G 0.0 0.0 0.0 0.0 0.0 0.0 0.0

H 0.0 0.0 0.0 0.0 0.0 0.0 0.0

I 0.0 0.0 0.0 0.0 0.0 0.0 0.0

J 0.0 0.0 0.0 0.0 0.0 0.0 0.0

K 0.0 0.0 0.0 0.0 0.0 0.0 0.0

L 0.0 0.0 0.0 0.0 0.0 0.0 0.0

M 0.0 0.0 0.0 0.0 0.0 0.0 0.0

In [96]: Index_label1 = actual_output.query('Monday==1').index.tolist()

print('Monday =',Index_label1)

Index_label2 = actual_output.query('Tuesday==1').index.tolist()
print('Tuesday =',Index_label2)

Index_label3 = actual_output.query('Wednesday==1').index.tolist()
print('Wednesday =',Index_label3)

Index_label4 = actual_output.query('Thursday==1').index.tolist()
print('Thursday =',Index_label4)

Index_label5 = actual_output.query('Friday==1').index.tolist()
print('Friday =',Index_label5)

Index_label6 = actual_output.query('Saturday==1').index.tolist()
print('Saturday =',Index_label6)

Index_label7 = actual_output.query('Sunday==1').index.tolist()
print('Sunday =',Index_label7)

Monday = ['A', 'B', 'C', 'D', 'E', 'F']

Tuesday = ['A', 'B', 'C', 'D', 'E', 'F']
Wednesday = ['A', 'B', 'C', 'D', 'E', 'F']
Thursday = ['A', 'B', 'C', 'D', 'E', 'F']
Friday = ['A', 'B', 'C', 'D', 'E', 'F']
Saturday = ['A', 'B', 'E', 'F']
Sunday = []

In [97]: buildings_to_clean=actual_output['Monday'].values.sum()
print(buildings_to_clean)

6.0

In [98]: import math

from random import *
import random

In [168… # generating nodes randomly

# since there are 13 buildings or nodes

num = 13
# radius of the circle (range of the wifi module)
circle_r = 50
# centre of the circle (x, y)
circle_x = 0
circle_y = 0

xy_list=[]
for i in range(num):
t = 2 * math.pi * random.random()
r = circle_r * math.sqrt(random.random())
x = r * math.cos(t) + circle_x
y = r * math.sin(t) + circle_y
xy_list.append([x,y])
circle_r = circle_r
# coordinate of the generated point is now the
# new centre of the circle
circle_x = x
circle_y = y

# connection between the nodes have been arbitrarily fixed

# however, the edges (distances) between them varies randomly.
xi=[xy_list[0][0], xy_list[1][0], xy_list[2][0], xy_list[3][0], xy_list[4][0], xy_list[5][0], xy_list[6][0],
xy_list[7][0], xy_list[8][0], xy_list[9][0], xy_list[10][0], xy_list[11][0], xy_list[12][0], xy_list[0][0],
xy_list[2][0], xy_list[4][0], xy_list[1][0], xy_list[3][0], xy_list[6][0], xy_list[9][0], xy_list[12][0],
xy_list[8][0], xy_list[5][0], xy_list[11][0], xy_list[7][0]]

yi=[xy_list[0][1], xy_list[1][1], xy_list[2][1], xy_list[3][1], xy_list[4][1], xy_list[5][1], xy_list[6][1],

xy_list[7][1], xy_list[8][1], xy_list[9][1], xy_list[10][1], xy_list[11][1], xy_list[12][1], xy_list[0][1],
xy_list[2][1], xy_list[4][1], xy_list[1][1], xy_list[3][1], xy_list[6][1], xy_list[9][1], xy_list[12][1],
xy_list[8][1], xy_list[5][1], xy_list[11][1], xy_list[7][1]]

n=['A','B','C','D','E','F','G','H','I','J','K','L','M']

fig, ax = plt.subplots()
ax.scatter(xi, yi,color='orange')
ax.plot(xi,yi,linestyle='dashed')
ax.set_title('Random Generated Graph')

for i, txt in enumerate(n):

ax.annotate(txt, (xi[i], yi[i]))

In [169… data={'Points':['A','B','C','D','E','F','G','H','I','J','K','L','M'],
'Coordinates':xy_list}

df=pd.DataFrame(data)
df

Out[169… Points Coordinates

0 A [-22.811352766369502, -42.9051483798065]

1 B [-16.548585957869044, -64.99301949290735]

2 C [-2.7135371843524982, -111.84658944434184]

3 D [14.504731245459316, -71.85514523206425]

4 E [52.616349152583524, -88.24676662203245]

5 F [83.45028968379334, -89.17275941357737]

6 G [112.04231553326235, -69.67377414401894]

7 H [138.77444345907816, -87.58117115205548]

8 I [104.70398680301169, -109.18049652906625]

9 J [65.50935819552903, -115.87765861437762]

10 K [19.718736052297082, -108.9197063224358]

11 L [47.22360087625079, -83.45634507275099]

12 M [73.86999598965316, -61.226726940341635]

In [170… # find the distance between the connected nodes

AB=math.sqrt( ((xy_list[0][0]-xy_list[1][0])**2)+((xy_list[0][1]-xy_list[1][1])**2) )

BC=math.sqrt( ((xy_list[1][0]-xy_list[2][0])**2)+((xy_list[1][1]-xy_list[2][1])**2) )

CD=math.sqrt( ((xy_list[2][0]-xy_list[3][0])**2)+((xy_list[2][1]-xy_list[3][1])**2) )

DE=math.sqrt( ((xy_list[3][0]-xy_list[4][0])**2)+((xy_list[3][1]-xy_list[4][1])**2) )

EF=math.sqrt( ((xy_list[4][0]-xy_list[5][0])**2)+((xy_list[4][1]-xy_list[5][1])**2) )

FG=math.sqrt( ((xy_list[5][0]-xy_list[6][0])**2)+((xy_list[5][1]-xy_list[6][1])**2) )

GH=math.sqrt( ((xy_list[6][0]-xy_list[7][0])**2)+((xy_list[6][1]-xy_list[7][1])**2) )

HI=math.sqrt( ((xy_list[7][0]-xy_list[8][0])**2)+((xy_list[7][1]-xy_list[8][1])**2) )

IJ=math.sqrt( ((xy_list[8][0]-xy_list[9][0])**2)+((xy_list[8][1]-xy_list[9][1])**2) )

JK=math.sqrt( ((xy_list[9][0]-xy_list[10][0])**2)+((xy_list[9][1]-xy_list[10][1])**2) )

KL=math.sqrt( ((xy_list[10][0]-xy_list[11][0])**2)+((xy_list[10][1]-xy_list[11][1])**2) )

LM=math.sqrt( ((xy_list[11][0]-xy_list[12][0])**2)+((xy_list[11][1]-xy_list[12][1])**2) )

MA=math.sqrt( ((xy_list[12][0]-xy_list[0][0])**2)+((xy_list[12][1]-xy_list[0][1])**2) )

AC=math.sqrt( ((xy_list[0][0]-xy_list[2][0])**2)+((xy_list[0][1]-xy_list[2][1])**2) )

CE=math.sqrt( ((xy_list[2][0]-xy_list[4][0])**2)+((xy_list[2][1]-xy_list[4][1])**2) )

EB=math.sqrt( ((xy_list[4][0]-xy_list[1][0])**2)+((xy_list[4][1]-xy_list[1][1])**2) )

BD=math.sqrt( ((xy_list[1][0]-xy_list[3][0])**2)+((xy_list[1][1]-xy_list[3][1])**2) )

DG=math.sqrt( ((xy_list[3][0]-xy_list[6][0])**2)+((xy_list[3][1]-xy_list[6][1])**2) )

GJ=math.sqrt( ((xy_list[6][0]-xy_list[9][0])**2)+((xy_list[6][1]-xy_list[9][1])**2) )

JM=math.sqrt( ((xy_list[9][0]-xy_list[12][0])**2)+((xy_list[9][1]-xy_list[12][1])**2) )

MI=math.sqrt( ((xy_list[12][0]-xy_list[8][0])**2)+((xy_list[12][1]-xy_list[8][1])**2) )

IF=math.sqrt( ((xy_list[8][0]-xy_list[5][0])**2)+((xy_list[8][1]-xy_list[5][1])**2) )

FL=math.sqrt( ((xy_list[5][0]-xy_list[11][0])**2)+((xy_list[5][1]-xy_list[11][1])**2) )

LH=math.sqrt( ((xy_list[11][0]-xy_list[7][0])**2)+((xy_list[11][1]-xy_list[7][1])**2) )

Nodes=['AB','BC','CD','DE','EF','FG','GH','HI','IJ','JK','KL','LM','MA','AC','CE','EB','BD','DG','GJ','JM','MI','IF','FL','LH']
Distance=[AB,BC,CD,DE,EF,FG,GH,HI,IJ,JK,KL,LM,MA,AC,CE,EB,BD,DG,GH,JM,MI,IF,FL,LH]
table=pd.DataFrame()
table['Nodes']=Nodes
table['Distance']=Distance
table

Out[170… Nodes Distance

0 AB 22.958578

1 BC 48.853512

2 CD 43.540606

3 DE 41.487115

4 EF 30.847842

5 FG 34.608010

6 GH 32.175791

7 HI 40.340140

8 IJ 39.762682

9 JK 46.316241

10 KL 37.482000

11 LM 34.701388

12 MA 98.402050

13 AC 71.811172

14 CE 60.152705

15 EB 72.969343

16 BD 31.802473

17 DG 97.561974

18 GJ 32.175791

19 JM 55.286749

20 MI 57.011394

21 IF 29.189539

22 FL 36.674928

23 LH 91.643718

In [173… import sys

from heapq import heappop, heappush

# A class to store a graph edge

class Edge:
def __init__(self, source, dest, weight):
self.source = source
self.dest = dest
self.weight = weight

# A class to store a heap node

class Node:
def __init__(self, vertex, weight):
self.vertex = vertex
self.weight = weight

# Override the `__lt__()` function to make `Node` class work with a min-heap
def __lt__(self, other):
return self.weight < other.weight

# A class to represent a graph object

class Graph:
def __init__(self, edges, N):
# allocate memory for the adjacency list
self.adj = [[] for _ in range(N)]

# add edges to the undirected graph

for edge in edges:
self.adj[edge.source].append(edge)

def get_route(prev, i, route):

if i >= 0:
# changing the value of integer i to corresponding character
node = chr(ord(root) + i)
get_route(prev, prev[i], route)
route.append(node)

# Run Dijkstra’s algorithm on a given graph

def findShortestPaths(graph, source, N):

# create a min-heap and push source node having distance 0

pq = []
heappush(pq, Node(source, 0))

# set initial distance from the source to `v` as INFINITY

dist = [sys.maxsize] * N

# distance from the source to itself is zero

dist[source] = 0

# list to track vertices for which minimum cost is already found

done = [False] * N
done[source] = True

# stores predecessor of a vertex (to a print path)

prev = [-1] * N
route = []

# run till min-heap is empty

while pq:

node = heappop(pq) # Remove and return the best vertex

u = node.vertex # get the vertex number

# do for each neighbor `v` of `u`

for edge in graph.adj[u]:
v = edge.dest
weight = edge.weight

# Relaxation step
if not done[v] and (dist[u] + weight) < dist[v]:
dist[v] = dist[u] + weight
prev[v] = u
heappush(pq, Node(v, dist[v]))

# mark vertex `u` as done so it will not get picked up again

done[u] = True

for i in range(1, N):

if i != source and dist[i] != sys.maxsize:
get_route(prev, i, route)
# changing the value of integer i to corresponding character
node = chr(ord(root) + i)
# Changed source to root and i to node
print(f"Path ({root} —> {node}): Minimum Distance = {dist[i]} Route = {route}")
route.clear()

if __name__ == '__main__':

# initialize edges as per the above diagram

# `(u, v, w)` triplet represent undirected edge from
# vertex `u` to vertex `v` having weight `w`
edges = [Edge(0,1,22.958578), Edge(0,2,71.811172), Edge(0,12,98.402050), Edge(1,2,48.853512), Edge(1,4,72.969343),
Edge(1,3,31.802473), Edge(2,3,43.5406062), Edge(2,4,60.152705), Edge(3,4,41.487115), Edge(3,6,97.561974),
Edge(4,5,30.847842), Edge(5,6,34.608010), Edge(5,8,29.189539), Edge(5,11,36.674928), Edge(6,7,32.175791),
Edge(6,9,32.175791), Edge(7,8,40.340140), Edge(7,11,91.643718), Edge(8,9,39.762682), Edge(8,12,57.011394),
Edge(9,10,46.316241), Edge(9,12,55.286749), Edge(10,11,37.482000), Edge(11,12,34.701388)]

# total number of nodes in the graph

N = 25

# construct graph
graph = Graph(edges, N)

source = 0
# a new variable 'root' as char data type
root = 'A'
findShortestPaths(graph, source, N)

Path (A —> B): Minimum Distance = 22.958578 Route = ['A', 'B']

Path (A —> C): Minimum Distance = 71.811172 Route = ['A', 'C']
Path (A —> D): Minimum Distance = 54.761050999999995 Route = ['A', 'B', 'D']
Path (A —> E): Minimum Distance = 95.927921 Route = ['A', 'B', 'E']
Path (A —> F): Minimum Distance = 126.775763 Route = ['A', 'B', 'E', 'F']
Path (A —> G): Minimum Distance = 152.323025 Route = ['A', 'B', 'D', 'G']
Path (A —> H): Minimum Distance = 184.498816 Route = ['A', 'B', 'D', 'G', 'H']
Path (A —> I): Minimum Distance = 155.965302 Route = ['A', 'B', 'E', 'F', 'I']
Path (A —> J): Minimum Distance = 184.498816 Route = ['A', 'B', 'D', 'G', 'J']
Path (A —> K): Minimum Distance = 230.815057 Route = ['A', 'B', 'D', 'G', 'J', 'K']
Path (A —> L): Minimum Distance = 163.450691 Route = ['A', 'B', 'E', 'F', 'L']
Path (A —> M): Minimum Distance = 98.40205 Route = ['A', 'M']

In [ ]: