notebook.community

Edit and run



In [1]:

    
#import needed packages
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 
import seaborn as sns
%matplotlib inline



In [2]:

    
#import data from URL
cred=pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/credit-screening/crx.data',\
                 header=None, names=['A1','A2','A3','A4','A5','A6','A7','A8','A9','A10','A11','A12',\
                                     'A13','A14','A15','A16'])



In [3]:

    
#look at data
cred.info()









    



<class 'pandas.core.frame.DataFrame'>
Int64Index: 690 entries, 0 to 689
Data columns (total 16 columns):
A1     690 non-null object
A2     690 non-null object
A3     690 non-null float64
A4     690 non-null object
A5     690 non-null object
A6     690 non-null object
A7     690 non-null object
A8     690 non-null float64
A9     690 non-null object
A10    690 non-null object
A11    690 non-null int64
A12    690 non-null object
A13    690 non-null object
A14    690 non-null object
A15    690 non-null int64
A16    690 non-null object
dtypes: float64(2), int64(2), object(12)
memory usage: 91.6+ KB



In [4]:

    
#check scatter of data
plt.scatter(cred.A3, cred.A8)









    Out[4]:





<matplotlib.collections.PathCollection at 0x10a877f90>



In [6]:

    
cred.A8.hist(by=cred['A16'], sharey=True, sharex=True)









    Out[6]:





array([<matplotlib.axes._subplots.AxesSubplot object at 0x10aa2a710>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x10acec6d0>], dtype=object)



In [7]:

    
cred.A7.value_counts().plot(kind='bar')









    Out[7]:





<matplotlib.axes._subplots.AxesSubplot at 0x10973e050>



In [8]:

    
approved_by_A4=cred.groupby('A4').A16.agg(['count'])
approved_by_A4



In [10]:

    
#observe data
cred.groupby(['A16'])['A4'].value_counts().plot(kind='bar')









    Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x10afb5910>



In [11]:

    
cred[cred.A14=='?']



In [12]:

    
#impute values for A2: average values
#convert '?' to 0.0
cred.A2.replace('?', 0.0, inplace=True)
cred[cred.A2=='0.0']



In [13]:

    
#convert string to float
cred.A2=cred.A2.astype(float)
cred.info()









    



<class 'pandas.core.frame.DataFrame'>
Int64Index: 690 entries, 0 to 689
Data columns (total 16 columns):
A1     690 non-null object
A2     690 non-null float64
A3     690 non-null float64
A4     690 non-null object
A5     690 non-null object
A6     690 non-null object
A7     690 non-null object
A8     690 non-null float64
A9     690 non-null object
A10    690 non-null object
A11    690 non-null int64
A12    690 non-null object
A13    690 non-null object
A14    690 non-null object
A15    690 non-null int64
A16    690 non-null object
dtypes: float64(3), int64(2), object(11)
memory usage: 91.6+ KB



In [14]:

    
#replace 0.0 with null values
cred.A2.replace(0.0, np.nan, inplace=True)
cred[pd.isnull(cred.A2)]



In [15]:

    
cred.A2.mean()









    Out[15]:





31.568171091445429



In [16]:

    
#replace A2 null values with mean
cred.A2.fillna(cred.A2.mean(), inplace=True)



In [17]:

    
#A14 does not look like numeric values so much as possible ID numbers.  If that is the case, it doesn't make much sense
#to impute average numeric values.  
cred.A14.replace('?', np.nan, inplace=True)
cred.A14=cred.A14.astype(float)
cred.info()









    



<class 'pandas.core.frame.DataFrame'>
Int64Index: 690 entries, 0 to 689
Data columns (total 16 columns):
A1     690 non-null object
A2     690 non-null float64
A3     690 non-null float64
A4     690 non-null object
A5     690 non-null object
A6     690 non-null object
A7     690 non-null object
A8     690 non-null float64
A9     690 non-null object
A10    690 non-null object
A11    690 non-null int64
A12    690 non-null object
A13    690 non-null object
A14    677 non-null float64
A15    690 non-null int64
A16    690 non-null object
dtypes: float64(4), int64(2), object(10)
memory usage: 91.6+ KB



In [18]:

    
cred.A14.plot()









    Out[18]:





<matplotlib.axes._subplots.AxesSubplot at 0x10b0e0810>



In [19]:

    
#exclude rows with missing A4, A5, A6, and A7 values
cred = cred[cred.A4 !='?']



In [20]:

    
#impute random choice for A1
#replace A1=? with null values
cred.A1.replace('?', np.nan, inplace=True)
cred[pd.isnull(cred.A1)]



In [21]:

    
#impute values for null observations
a1_missing_mask = cred.A1.isnull()
cred[a1_missing_mask]



In [22]:

    
cred.loc[cred.A1.isnull(), 'A1'] = np.random.choice(cred.A1, 12)



In [23]:

    
cred.A1.values









    Out[23]:





array(['b', 'a', 'a', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b', 'a',
       'b', 'a', 'b', 'b', 'a', 'b', 'a', 'b', 'b', 'a', 'a', 'a', 'a',
       'a', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'b', 'a', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'a', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b',
       'b', 'a', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b', 'a',
       'b', 'b', 'b', 'a', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'a', 'b',
       'b', 'b', 'b', 'b', 'a', 'b', 'b', 'a', 'a', 'b', 'b', 'b', 'b',
       'b', 'b', 'b', 'a', 'b', 'a', 'b', 'a', 'b', 'a', 'b', 'a', 'b',
       'b', 'b', 'a', 'b', 'b', 'a', 'a', 'a', 'b', 'b', 'b', 'b', 'a',
       'b', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'a', 'a', 'b',
       'b', 'b', 'b', 'b', 'a', 'a', 'a', 'a', 'a', 'b', 'b', 'b', 'a',
       'a', 'a', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'a', 'b',
       'b', 'a', 'b', 'b', 'a', 'b', 'b', 'b', 'a', 'a', 'b', 'b', 'a',
       'a', 'a', 'a', 'b', 'b', 'b', 'a', 'a', 'b', 'b', 'b', 'b', 'b',
       'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'a', 'b', 'a', 'b', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b',
       'a', 'a', 'a', 'b', 'b', 'a', 'b', 'b', 'b', 'a', 'b', 'b', 'a',
       'a', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'a',
       'a', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b',
       'a', 'a', 'a', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'b',
       'b', 'a', 'a', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'a', 'b',
       'b', 'a', 'b', 'a', 'b', 'b', 'a', 'a', 'b', 'b', 'b', 'b', 'a',
       'b', 'b', 'a', 'a', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'a', 'a',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'b', 'a', 'b',
       'a', 'b', 'b', 'a', 'b', 'a', 'b', 'b', 'b', 'a', 'a', 'b', 'a',
       'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'a', 'b', 'b', 'b',
       'b', 'a', 'b', 'a', 'b', 'a', 'a', 'b', 'b', 'b', 'b', 'b', 'a',
       'b', 'a', 'b', 'b', 'b', 'a', 'b', 'b', 'a', 'b', 'b', 'b', 'b',
       'b', 'a', 'a', 'a', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b',
       'b', 'b', 'a', 'b', 'a', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'a',
       'a', 'a', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'a', 'b', 'b', 'b',
       'a', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b', 'b',
       'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'b', 'b', 'b', 'b', 'a',
       'a', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b',
       'b', 'a', 'b', 'b', 'a', 'a', 'a', 'b', 'a', 'b', 'b', 'a', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'a', 'b', 'b',
       'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'a', 'a', 'b', 'a', 'b',
       'b', 'b', 'b', 'b', 'a', 'b', 'a', 'b', 'a', 'a', 'a', 'b', 'b',
       'a', 'a', 'b', 'b', 'b', 'a', 'b', 'a', 'b', 'b', 'a', 'b', 'a',
       'a', 'b', 'b', 'a', 'a', 'b', 'a', 'a', 'b', 'b', 'b', 'a', 'a',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b',
       'b', 'b', 'b', 'b', 'a', 'b', 'b', 'a', 'b', 'a', 'a', 'b', 'b',
       'b', 'b', 'a', 'b', 'a', 'b', 'a', 'b', 'b', 'b', 'a', 'a', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b', 'b', 'b', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'a', 'a', 'b', 'b', 'a', 'b', 'b',
       'b', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b',
       'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'a',
       'a', 'a', 'a', 'b', 'a', 'b', 'b', 'b', 'b', 'b', 'b', 'a', 'b',
       'a', 'b', 'b', 'a', 'b', 'b', 'a', 'b', 'a', 'a', 'b', 'a', 'a',
       'b', 'a', 'a', 'a', 'b', 'b', 'a', 'b', 'b', 'b', 'a', 'a', 'b',
       'b', 'b', 'b', 'a', 'b', 'a', 'a', 'a', 'b', 'a', 'a', 'b', 'b',
       'b', 'b', 'b', 'b', 'a', 'a', 'b', 'b'], dtype=object)

#Logistic Regression



In [24]:

    
X_data = cred[['A2','A3','A4','A5','A6','A7','A8','A9','A10','A11','A12',\
                                     'A13','A14','A15','A1']]



In [25]:

    
X_data.info()









    



<class 'pandas.core.frame.DataFrame'>
Int64Index: 684 entries, 0 to 689
Data columns (total 15 columns):
A2     684 non-null float64
A3     684 non-null float64
A4     684 non-null object
A5     684 non-null object
A6     684 non-null object
A7     684 non-null object
A8     684 non-null float64
A9     684 non-null object
A10    684 non-null object
A11    684 non-null int64
A12    684 non-null object
A13    684 non-null object
A14    677 non-null float64
A15    684 non-null int64
A1     684 non-null object
dtypes: float64(4), int64(2), object(9)
memory usage: 85.5+ KB



In [26]:

    
X_data = pd.get_dummies(X_data)



In [27]:

    
y_data = cred[['A16']]



In [28]:

    
y_data









    Out[28]:






  
    
      
      A16
    
  
  
    
      0  
       +
    
    
      1  
       +
    
    
      2  
       +
    
    
      3  
       +
    
    
      4  
       +
    
    
      5  
       +
    
    
      6  
       +
    
    
      7  
       +
    
    
      8  
       +
    
    
      9  
       +
    
    
      10 
       +
    
    
      11 
       +
    
    
      12 
       +
    
    
      13 
       +
    
    
      14 
       +
    
    
      15 
       +
    
    
      16 
       +
    
    
      17 
       +
    
    
      18 
       +
    
    
      19 
       +
    
    
      20 
       +
    
    
      21 
       +
    
    
      22 
       +
    
    
      23 
       +
    
    
      24 
       +
    
    
      25 
       +
    
    
      26 
       +
    
    
      27 
       +
    
    
      28 
       +
    
    
      29 
       +
    
    
      ...
      ...
    
    
      660
       -
    
    
      661
       -
    
    
      662
       -
    
    
      663
       -
    
    
      664
       -
    
    
      665
       -
    
    
      666
       -
    
    
      667
       -
    
    
      668
       -
    
    
      669
       -
    
    
      670
       -
    
    
      671
       -
    
    
      672
       -
    
    
      673
       -
    
    
      674
       -
    
    
      675
       -
    
    
      676
       -
    
    
      677
       -
    
    
      678
       -
    
    
      679
       -
    
    
      680
       -
    
    
      681
       -
    
    
      682
       -
    
    
      683
       -
    
    
      684
       -
    
    
      685
       -
    
    
      686
       -
    
    
      687
       -
    
    
      688
       -
    
    
      689
       -
    
  

684 rows × 1 columns



In [29]:

    
from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LogisticRegression



In [30]:

    
X_train, X_test, y_train, y_test = train_test_split(X_data, y_data, random_state=12, test_size=0.2)



In [31]:

    
clf = LogisticRegression()



In [32]:

    
y_train=np.ravel(y_train)



In [33]:

    
clf.fit(X_train, y_train)









    



---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-33-48a2aac41443> in <module>()
----> 1 clf.fit(X_train, y_train)

/Users/danielallgeier/anaconda/lib/python2.7/site-packages/sklearn/svm/base.pyc in fit(self, X, y)
    677                              " one.")
    678 
--> 679         X = atleast2d_or_csr(X, dtype=np.float64, order="C")
    680 
    681         self.class_weight_ = compute_class_weight(self.class_weight,

/Users/danielallgeier/anaconda/lib/python2.7/site-packages/sklearn/utils/validation.pyc in atleast2d_or_csr(X, dtype, order, copy, force_all_finite)
    163     return _atleast2d_or_sparse(X, dtype, order, copy, sp.csr_matrix,
    164                                 "tocsr", sp.isspmatrix_csr,
--> 165                                 force_all_finite)
    166 
    167 

/Users/danielallgeier/anaconda/lib/python2.7/site-packages/sklearn/utils/validation.pyc in _atleast2d_or_sparse(X, dtype, order, copy, sparse_class, convmethod, check_same_type, force_all_finite)
    140     else:
    141         X = array2d(X, dtype=dtype, order=order, copy=copy,
--> 142                     force_all_finite=force_all_finite)
    143     return X
    144 

/Users/danielallgeier/anaconda/lib/python2.7/site-packages/sklearn/utils/validation.pyc in array2d(X, dtype, order, copy, force_all_finite)
    120     X_2d = np.asarray(np.atleast_2d(X), dtype=dtype, order=order)
    121     if force_all_finite:
--> 122         _assert_all_finite(X_2d)
    123     if X is X_2d and copy:
    124         X_2d = safe_copy(X_2d)

/Users/danielallgeier/anaconda/lib/python2.7/site-packages/sklearn/utils/validation.pyc in _assert_all_finite(X)
     41             and not np.isfinite(X).all()):
     42         raise ValueError("Input contains NaN, infinity"
---> 43                          " or a value too large for %r." % X.dtype)
     44 
     45 

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').



In [129]:

    
clf.score(X_test, y_test)









    Out[129]:





0.86131386861313863

#SVM



In [122]:

    
from sklearn.svm import LinearSVC



In [123]:

    
#initialize C=1e-3
est= LinearSVC(C=4.64e-3)



In [124]:

    
est.fit(X_train, y_train)









    Out[124]:





LinearSVC(C=0.00464, class_weight=None, dual=True, fit_intercept=True,
     intercept_scaling=1, loss='l2', multi_class='ovr', penalty='l2',
     random_state=None, tol=0.0001, verbose=0)



In [125]:

    
est.score(X_test, y_test)









    Out[125]:





0.83211678832116787

Grid Search



In [108]:

    
from sklearn.grid_search import GridSearchCV



In [109]:

    
d={}
d['C']=np.logspace(-3, 3, 10)
d
#traverses the logspace of 10^-3 to 10^3 for 10 values









    Out[109]:





{'C': array([  1.00000000e-03,   4.64158883e-03,   2.15443469e-02,
          1.00000000e-01,   4.64158883e-01,   2.15443469e+00,
          1.00000000e+01,   4.64158883e+01,   2.15443469e+02,
          1.00000000e+03])}



In [110]:

    
gs= GridSearchCV(LinearSVC(), d)



In [111]:

    
gs.fit(X_train, y_train)
#fits values of C using our dictionary parameter









    Out[111]:





GridSearchCV(cv=None,
       estimator=LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,
     intercept_scaling=1, loss='l2', multi_class='ovr', penalty='l2',
     random_state=None, tol=0.0001, verbose=0),
       fit_params={}, iid=True, loss_func=None, n_jobs=1,
       param_grid={'C': array([  1.00000e-03,   4.64159e-03,   2.15443e-02,   1.00000e-01,
         4.64159e-01,   2.15443e+00,   1.00000e+01,   4.64159e+01,
         2.15443e+02,   1.00000e+03])},
       pre_dispatch='2*n_jobs', refit=True, score_func=None, scoring=None,
       verbose=0)



In [112]:

    
#find the best parameter
gs.best_params_, gs.best_score_









    Out[112]:





({'C': 0.0046415888336127772}, 0.84826325411334547)

Confusion Matrix



In [113]:

    
#Confusion Matrix
from sklearn.metrics import confusion_matrix, classification_report



In [114]:

    
y_pred = clf.predict(X_test)



In [115]:

    
# Confusion Matrix for Type 1 and Type 2 Error
#a and d are the correct predictions, b and c are incorrect predictions
confusion_matrix(y_test, y_pred)









    Out[115]:





array([[51,  8],
       [11, 67]])



In [116]:

    
# Examine Precision and Recall
print classification_report(y_test, y_pred)









    



             precision    recall  f1-score   support

          +       0.82      0.86      0.84        59
          -       0.89      0.86      0.88        78

avg / total       0.86      0.86      0.86       137



In [117]:

    
# examine the coefficients and significance of Variables
pd.DataFrame(zip(X_data.columns, np.transpose(clf.coef_)))









    Out[117]:






  
    
      
      0
      1
    
  
  
    
      0  
              A2
          [0.0150744279478]
    
    
      1  
              A3
          [0.0016942926819]
    
    
      2  
              A8
         [-0.0974029449517]
    
    
      3  
             A11
          [-0.108922358405]
    
    
      4  
             A15
       [-0.000486604063634]
    
    
      5  
            A4_l
          [-0.517841781245]
    
    
      6  
            A4_u
            [0.16385786763]
    
    
      7  
            A4_y
           [0.480871443674]
    
    
      8  
            A5_g
            [0.16385786763]
    
    
      9  
           A5_gg
          [-0.517841781245]
    
    
      10 
            A5_p
           [0.480871443674]
    
    
      11 
            A6_?
           [0.439883244977]
    
    
      12 
           A6_aa
           [0.381730168583]
    
    
      13 
            A6_c
         [-0.0394058537519]
    
    
      14 
           A6_cc
          [-0.469143898849]
    
    
      15 
            A6_d
           [0.806687546733]
    
    
      16 
            A6_e
          [-0.224601393159]
    
    
      17 
           A6_ff
           [0.845429908251]
    
    
      18 
            A6_i
           [0.348583187069]
    
    
      19 
            A6_j
           [0.366162541518]
    
    
      20 
            A6_k
          [0.0713997670217]
    
    
      21 
            A6_m
         [-0.0573671502626]
    
    
      22 
            A6_q
          [-0.404400380504]
    
    
      23 
            A6_r
        [-0.00896083119211]
    
    
      24 
            A6_w
           [-0.48891879855]
    
    
      25 
            A6_x
           [-1.44019052783]
    
    
      26 
            A7_?
           [0.439883244977]
    
    
      27 
           A7_bb
           [0.174366162242]
    
    
      28 
           A7_dd
         [-0.0640283800956]
    
    
      29 
           A7_ff
           [0.297523257064]
    
    
      ...
      ...
      ...
    
    
      188
       A14_00455
         [-0.0212867395138]
    
    
      189
       A14_00460
           [0.104538252419]
    
    
      190
       A14_00465
          [0.0671650237337]
    
    
      191
       A14_00470
         [-0.0713471055503]
    
    
      192
       A14_00480
          [0.0377458462181]
    
    
      193
       A14_00487
           [-0.16593023219]
    
    
      194
       A14_00491
          [-0.267155072612]
    
    
      195
       A14_00500
          [-0.856741018441]
    
    
      196
       A14_00510
          [-0.116495579437]
    
    
      197
       A14_00515
                      [0.0]
    
    
      198
       A14_00519
          [-0.014267421699]
    
    
      199
       A14_00520
         [-0.0270930232267]
    
    
      200
       A14_00523
           [0.459526760006]
    
    
      201
       A14_00550
                      [0.0]
    
    
      202
       A14_00560
          [-0.382930835601]
    
    
      203
       A14_00583
         [-0.0260452865932]
    
    
      204
       A14_00600
                      [0.0]
    
    
      205
       A14_00640
           [0.116804741738]
    
    
      206
       A14_00680
                      [0.0]
    
    
      207
       A14_00711
          [-0.599259996514]
    
    
      208
       A14_00720
          [0.0628433573896]
    
    
      209
       A14_00760
           [0.671513703041]
    
    
      210
       A14_00840
          [-0.144389416088]
    
    
      211
       A14_00928
           [0.307807690087]
    
    
      212
       A14_00980
            [0.71491929575]
    
    
      213
       A14_01160
          [0.0209150603453]
    
    
      214
       A14_02000
          [0.0430429192188]
    
    
      215
           A14_?
          [0.0653349310692]
    
    
      216
            A1_a
          [0.0677193899333]
    
    
      217
            A1_b
          [0.0591681401253]
    
  

218 rows × 2 columns



In [ ]:

	A1	A2	A3	A4	A5	A6	A7	A8	A9	A10	A11	A12	A13	A14	A15	A16
71	b	34.83	4.000	u	g	d	bb	12.500	t	f	0	t	g	?	0	-
202	b	24.83	2.750	u	g	c	v	2.250	t	t	6	f	g	?	600	+
206	a	71.58	0.000	?	?	?	?	0.000	f	f	0	f	p	?	0	+
243	a	18.75	7.500	u	g	q	v	2.710	t	t	5	f	g	?	26726	+
270	b	37.58	0.000	?	?	?	?	0.000	f	f	0	f	p	?	0	+
278	b	24.58	13.500	y	p	ff	ff	0.000	f	f	0	f	g	?	0	-
330	b	20.42	0.000	?	?	?	?	0.000	f	f	0	f	p	?	0	-
406	a	40.33	8.125	y	p	k	v	0.165	f	t	2	f	g	?	18	-
445	a	?	11.250	u	g	ff	ff	0.000	f	f	0	f	g	?	5200	-
456	b	34.58	0.000	?	?	?	?	0.000	f	f	0	f	p	?	0	-
592	b	23.17	0.000	?	?	?	?	0.000	f	f	0	f	p	?	0	+
622	a	25.58	0.000	?	?	?	?	0.000	f	f	0	f	p	?	0	+
626	b	22.00	7.835	y	p	i	bb	0.165	f	f	0	t	g	?	0	-

	A1	A2	A3	A4	A5	A6	A7	A8	A9	A10	A11	A12	A13	A14	A15	A16
83	a	NaN	3.500	u	g	d	v	3.000	t	f	0	t	g	00300	0	-
86	b	NaN	0.375	u	g	d	v	0.875	t	f	0	t	s	00928	0	-
92	b	NaN	5.000	y	p	aa	v	8.500	t	f	0	f	g	00000	0	-
97	b	NaN	0.500	u	g	c	bb	0.835	t	f	0	t	s	00320	0	-
254	b	NaN	0.625	u	g	k	v	0.250	f	f	0	f	g	00380	2010	-
286	a	NaN	1.500	u	g	ff	ff	0.000	f	t	2	t	g	00200	105	-
329	b	NaN	4.000	y	p	i	v	0.085	f	f	0	t	g	00411	0	-
445	a	NaN	11.250	u	g	ff	ff	0.000	f	f	0	f	g	?	5200	-
450	b	NaN	3.000	y	p	i	bb	7.000	f	f	0	f	g	00000	1	-
500	b	NaN	4.000	u	g	x	v	5.000	t	t	3	t	g	00290	2279	+
515	b	NaN	10.500	u	g	x	v	6.500	t	f	0	f	g	00000	0	+
608	b	NaN	0.040	y	p	d	v	4.250	f	f	0	t	g	00460	0	-

	A1	A2	A3	A4	A5	A6	A7	A8	A9	A10	A11	A12	A13	A14	A15	A16
248	NaN	24.50	12.750	u	g	c	bb	4.750	t	t	2	f	g	73	444	+
327	NaN	40.83	3.500	u	g	i	bb	0.500	f	f	0	f	s	1160	0	-
346	NaN	32.25	1.500	u	g	c	v	0.250	f	f	0	t	g	372	122	-
374	NaN	28.17	0.585	u	g	aa	v	0.040	f	f	0	f	g	260	1004	-
453	NaN	29.75	0.665	u	g	w	v	0.250	f	f	0	t	g	300	0	-
479	NaN	26.50	2.710	y	p	?	?	0.085	f	f	0	f	s	80	0	-
489	NaN	45.33	1.000	u	g	q	v	0.125	f	f	0	t	g	263	0	-
520	NaN	20.42	7.500	u	g	k	v	1.500	t	t	1	f	g	160	234	+
598	NaN	20.08	0.125	u	g	q	v	1.000	f	t	1	f	g	240	768	+
601	NaN	42.25	1.750	y	p	?	?	0.000	f	f	0	t	g	150	1	-
641	NaN	33.17	2.250	y	p	cc	v	3.500	f	f	0	t	g	200	141	-
673	NaN	29.50	2.000	y	p	e	h	2.000	f	f	0	f	g	256	17	-

	A16
0	+
1	+
2	+
3	+
4	+
5	+
6	+
7	+
8	+
9	+
10	+
11	+
12	+
13	+
14	+
15	+
16	+
17	+
18	+
19	+
20	+
21	+
22	+
23	+
24	+
25	+
26	+
27	+
28	+
29	+
...	...
660	-
661	-
662	-
663	-
664	-
665	-
666	-
667	-
668	-
669	-
670	-
671	-
672	-
673	-
674	-
675	-
676	-
677	-
678	-
679	-
680	-
681	-
682	-
683	-
684	-
685	-
686	-
687	-
688	-
689	-

	0	1
0	A2	[0.0150744279478]
1	A3	[0.0016942926819]
2	A8	[-0.0974029449517]
3	A11	[-0.108922358405]
4	A15	[-0.000486604063634]
5	A4_l	[-0.517841781245]
6	A4_u	[0.16385786763]
7	A4_y	[0.480871443674]
8	A5_g	[0.16385786763]
9	A5_gg	[-0.517841781245]
10	A5_p	[0.480871443674]
11	A6_?	[0.439883244977]
12	A6_aa	[0.381730168583]
13	A6_c	[-0.0394058537519]
14	A6_cc	[-0.469143898849]
15	A6_d	[0.806687546733]
16	A6_e	[-0.224601393159]
17	A6_ff	[0.845429908251]
18	A6_i	[0.348583187069]
19	A6_j	[0.366162541518]
20	A6_k	[0.0713997670217]
21	A6_m	[-0.0573671502626]
22	A6_q	[-0.404400380504]
23	A6_r	[-0.00896083119211]
24	A6_w	[-0.48891879855]
25	A6_x	[-1.44019052783]
26	A7_?	[0.439883244977]
27	A7_bb	[0.174366162242]
28	A7_dd	[-0.0640283800956]
29	A7_ff	[0.297523257064]
...	...	...
188	A14_00455	[-0.0212867395138]
189	A14_00460	[0.104538252419]
190	A14_00465	[0.0671650237337]
191	A14_00470	[-0.0713471055503]
192	A14_00480	[0.0377458462181]
193	A14_00487	[-0.16593023219]
194	A14_00491	[-0.267155072612]
195	A14_00500	[-0.856741018441]
196	A14_00510	[-0.116495579437]
197	A14_00515	[0.0]
198	A14_00519	[-0.014267421699]
199	A14_00520	[-0.0270930232267]
200	A14_00523	[0.459526760006]
201	A14_00550	[0.0]
202	A14_00560	[-0.382930835601]
203	A14_00583	[-0.0260452865932]
204	A14_00600	[0.0]
205	A14_00640	[0.116804741738]
206	A14_00680	[0.0]
207	A14_00711	[-0.599259996514]
208	A14_00720	[0.0628433573896]
209	A14_00760	[0.671513703041]
210	A14_00840	[-0.144389416088]
211	A14_00928	[0.307807690087]
212	A14_00980	[0.71491929575]
213	A14_01160	[0.0209150603453]
214	A14_02000	[0.0430429192188]
215	A14_?	[0.0653349310692]
216	A1_a	[0.0677193899333]
217	A1_b	[0.0591681401253]

	A16
0	+
1	+
2	+
3	+
4	+
5	+
6	+
7	+
8	+
9	+
10	+
11	+
12	+
13	+
14	+
15	+
16	+
17	+
18	+
19	+
20	+
21	+
22	+
23	+
24	+
25	+
26	+
27	+
28	+
29	+
...	...
660	-
661	-
662	-
663	-
664	-
665	-
666	-
667	-
668	-
669	-
670	-
671	-
672	-
673	-
674	-
675	-
676	-
677	-
678	-
679	-
680	-
681	-
682	-
683	-
684	-
685	-
686	-
687	-
688	-
689	-

	A16
0	+
1	+
2	+
3	+
4	+
5	+
6	+
7	+
8	+
9	+
10	+
11	+
12	+
13	+
14	+
15	+
16	+
17	+
18	+
19	+
20	+
21	+
22	+
23	+
24	+
25	+
26	+
27	+
28	+
29	+
...	...
660	-
661	-
662	-
663	-
664	-
665	-
666	-
667	-
668	-
669	-
670	-
671	-
672	-
673	-
674	-
675	-
676	-
677	-
678	-
679	-
680	-
681	-
682	-
683	-
684	-
685	-
686	-
687	-
688	-
689	-