SVC Unable to find the attributes '_probA'

Question

I am developing credit card fraud detections project in machine learning. I have download the code form GitHub (https://github.com/devrajkataria/Credit-Card-Fraud-Detection-ML-WebApp) but I am getting following errors:

AttributeError: 'SVC' object has no attribute '_probA'

I tried to update the package but the did not work .I am using python version of 3.6. Here is the code.py

import numpy as np
import sklearn
from flask import Flask, request, jsonify, render_template
import pickle
from sklearn.svm import SVC

    app = Flask(__name__)
    # prediction function 
    def ValuePredictor(to_predict_list): 
        to_predict = np.array(to_predict_list).reshape(1, 7) 
        loaded_model = pickle.load(open("model.pkl", "rb")) 
        result = loaded_model.predict(to_predict) 
        return result[0]     
        
    @app.route('/')
    def home():
        return render_template("index.html")
    
    @app.route('/predict',methods=['POST','GET'])
    def predict():
        if request.method == 'POST':
            to_predict_list = request.form.to_dict() 
            to_predict_list = list(to_predict_list.values()) 
            to_predict_list = list(map(float, to_predict_list))
            result = ValuePredictor(to_predict_list)
        if int(result)== 1:
            prediction ='Given transaction is fradulent'
        else:
            prediction ='Given transaction is NOT fradulent'            
        return render_template("result.html", prediction = prediction) 
               
                      
    if __name__ == "__main__":
        app.run(debug=True)

Here is the classifier code.

# -*- coding: utf-8 -*-
"""Project_Final.ipynb

Automatically generated by Colaboratory.

# Data Preprocessing and Visualisation
"""

# Commented out IPython magic to ensure Python compatibility.
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
import seaborn as sns 
# %matplotlib inline

# Commented out IPython magic to ensure Python compatibility.
import sklearn
import random

from sklearn.utils import shuffle
# %matplotlib inline

from zipfile import ZipFile
with ZipFile('creditcardfraud.zip','r') as zip:
  zip.printdir()
  zip.extractall()

d=pd.read_csv('creditcard.csv')

sns.distplot(data['Amount'])

sns.distplot(data['Time'])

data.hist(figsize=(20,20))
plt.show()

sns.jointplot(x= 'Time', y= 'Amount', data= d)

class0 = d[d['Class']==0]

len(class0)

class1 = d[d['Class']==1]

len(class1)

class0
temp = shuffle(class0)

d1 = temp.iloc[:2000,:]

d1

frames = [d1, class1]
df_temp = pd.concat(frames)

df_temp.info()

df= shuffle(df_temp)

df.to_csv('creditcardsampling.csv')

sns.countplot('Class', data=df)

"""# SMOTE"""

!pip install --user imblearn

import imblearn

from imblearn.over_sampling import  SMOTE
oversample=SMOTE()
X=df.iloc[ : ,:-1]
Y=df.iloc[: , -1]
X,Y=oversample.fit_resample(X,Y)

X=pd.DataFrame(X)
X.shape

Y=pd.DataFrame(Y)
Y.head()

names=['Time','V1','V2','V3','V4','V5','V6','V7','V8','V9','V10','V11','V12','V13','V14','V15','V16','V17','V18','V19','V20','V21','V22','V23','V24','V25','V26','V27','V28','Amount','Class']

data=pd.concat([X,Y],axis=1)

d=data.values

data=pd.DataFrame(d,columns=names)

sns.countplot('Class', data=data)

data.describe()

data.info()

plt.figure(figsize=(12,10))
sns.heatmap(data.corr())

!pip install --user lightgbm

!pip install --user utils

import math
import sklearn.preprocessing

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score , classification_report, confusion_matrix, precision_recall_curve, f1_score, auc

X_train, X_test, y_train, y_test = train_test_split(data.drop('Class', axis=1), data['Class'], test_size=0.3, random_state=42)

"""# Feature Scaling"""

cols= ['V22', 'V24', 'V25', 'V26', 'V27', 'V28']

scaler = StandardScaler()

frames= ['Time', 'Amount']

x= data[frames]

d_temp = data.drop(frames, axis=1)

temp_col=scaler.fit_transform(x)

scaled_col = pd.DataFrame(temp_col, columns=frames)

scaled_col.head()

d_scaled = pd.concat([scaled_col, d_temp], axis =1)

d_scaled.head()

y = data['Class']

d_scaled.head()

"""# Dimensionality Reduction"""

from sklearn.decomposition import PCA

pca = PCA(n_components=7)

X_temp_reduced = pca.fit_transform(d_scaled)

pca.explained_variance_ratio_

pca.explained_variance_

names=['Time','Amount','Transaction Method','Transaction Id','Location','Type of Card','Bank']

X_reduced= pd.DataFrame(X_temp_reduced,columns=names)
X_reduced.head()

Y=d_scaled['Class']

new_data=pd.concat([X_reduced,Y],axis=1)
new_data.head()
new_data.shape

new_data.to_csv('finaldata.csv')

X_train, X_test, y_train, y_test= train_test_split(X_reduced, d_scaled['Class'], test_size = 0.30, random_state = 42)

X_train.shape, X_test.shape

"""# Logistic Regression"""

from sklearn.linear_model import LogisticRegression
lr=LogisticRegression()
lr.fit(X_train,y_train)
y_pred_lr=lr.predict(X_test)
y_pred_lr

from sklearn.metrics import classification_report,confusion_matrix
print(confusion_matrix(y_test,y_pred_lr))

#Hyperparamter tuning 
from sklearn.model_selection import GridSearchCV
lr_model = LogisticRegression()
lr_params = {'penalty': ['l1', 'l2'],'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000]}
grid_lr= GridSearchCV(lr_model, param_grid = lr_params)
grid_lr.fit(X_train, y_train)

grid_lr.best_params_

y_pred_lr3=grid_lr.predict(X_test)
print(classification_report(y_test,y_pred_lr3))



"""# Support Vector Machine"""

from sklearn.svm import SVC
svc=SVC(kernel='rbf')
svc.fit(X_train,y_train)
y_pred_svc=svc.predict(X_test)
y_pred_svc

print(classification_report(y_test,y_pred_svc))

print(confusion_matrix(y_test,y_pred_svc))

from sklearn.model_selection import GridSearchCV
parameters = [ {'C': [1, 10, 100, 1000], 'kernel': ['rbf'], 'gamma': [0.1, 1, 0.01, 0.0001 ,0.001]}]
grid_search = GridSearchCV(estimator = svc,
                           param_grid = parameters,
                           scoring = 'accuracy',
                           n_jobs = -1)
grid_search = grid_search.fit(X_train, y_train)
best_accuracy = grid_search.best_score_
best_parameters = grid_search.best_params_
print("Best Accuracy: {:.2f} %".format(best_accuracy*100))
print("Best Parameters:", best_parameters)

svc_param=SVC(kernel='rbf',gamma=0.01,C=100)
svc_param.fit(X_train,y_train)
y_pred_svc2=svc_param.predict(X_test)
print(classification_report(y_test,y_pred_svc2))



"""# Decision Tree"""

from sklearn.tree import DecisionTreeClassifier
dtree=DecisionTreeClassifier()
dtree.fit(X_train,y_train)
y_pred_dtree=dtree.predict(X_test)
print(classification_report(y_test,y_pred_dtree))

Model code...

# Commented out IPython magic to ensure Python compatibility.
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
import seaborn as sns 
# %matplotlib inline

# Commented out IPython magic to ensure Python compatibility.
import sklearn
import random

from sklearn.utils import shuffle
# %matplotlib inline


data=pd.read_csv('creditcard.csv')

sns.distplot(data['Amount'])

sns.distplot(data['Time'])

data.hist(figsize=(20,20))
plt.show()

sns.jointplot(x= 'Time', y= 'Amount', data= d)
d=data
class0 = d[d['Class']==0]

len(class0)

class1 = d[d['Class']==1]

len(class1)

class0
temp = shuffle(class0)

d1 = temp.iloc[:2000,:]

d1

frames = [d1, class1]
df_temp = pd.concat(frames)

df_temp.info()

df= shuffle(df_temp)

df.to_csv('creditcardsampling.csv')

sns.countplot('Class', data=df)

"""# SMOTE"""

#!pip install --user imblearn

import imblearn

from imblearn.over_sampling import  SMOTE
oversample=SMOTE()
X=df.iloc[ : ,:-1]
Y=df.iloc[: , -1]
X,Y=oversample.fit_resample(X,Y)

X=pd.DataFrame(X)
X.shape

Y=pd.DataFrame(Y)
Y.head()

names=['Time','V1','V2','V3','V4','V5','V6','V7','V8','V9','V10','V11','V12','V13','V14','V15','V16','V17','V18','V19','V20','V21','V22','V23','V24','V25','V26','V27','V28','Amount','Class']

data=pd.concat([X,Y],axis=1)

d=data.values

data=pd.DataFrame(d,columns=names)

sns.countplot('Class', data=data)

data.describe()

data.info()

plt.figure(figsize=(12,10))
sns.heatmap(data.corr())


import math
import sklearn.preprocessing

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score , classification_report, confusion_matrix, precision_recall_curve, f1_score, auc

X_train, X_test, y_train, y_test = train_test_split(data.drop('Class', axis=1), data['Class'], test_size=0.3, random_state=42)

"""# Feature Scaling"""

cols= ['V22', 'V24', 'V25', 'V26', 'V27', 'V28']

scaler = StandardScaler()

frames= ['Time', 'Amount']

x= data[frames]

d_temp = data.drop(frames, axis=1)

temp_col=scaler.fit_transform(x)

scaled_col = pd.DataFrame(temp_col, columns=frames)

scaled_col.head()

d_scaled = pd.concat([scaled_col, d_temp], axis =1)

d_scaled.head()

y = data['Class']

d_scaled.head()

"""# Dimensionality Reduction"""

from sklearn.decomposition import PCA

pca = PCA(n_components=7)

X_temp_reduced = pca.fit_transform(d_scaled)

pca.explained_variance_ratio_

pca.explained_variance_

names=['Time','Amount','Transaction Method','Transaction Id','Location','Type of Card','Bank']

X_reduced= pd.DataFrame(X_temp_reduced,columns=names)
X_reduced.head()

Y=d_scaled['Class']

new_data=pd.concat([X_reduced,Y],axis=1)
new_data.head()
new_data.shape

new_data.to_csv('finaldata.csv')

X_train, X_test, y_train, y_test= train_test_split(X_reduced, d_scaled['Class'], test_size = 0.30, random_state = 42)

X_train.shape, X_test.shape

from sklearn.metrics import classification_report,confusion_matrix


"""# Support Vector Machine"""

from sklearn.svm import SVC
svc=SVC(kernel='rbf',probability=True)
svc.fit(X_train,y_train)
y_pred_svc=svc.predict(X_test)
y_pred_svc

type(X_test)
X_test.to_csv('testing.csv')
from sklearn.model_selection import GridSearchCV
parameters = [ {'C': [1, 10, 100, 1000], 'kernel': ['rbf'], 'gamma': [0.1, 1, 0.01, 0.0001 ,0.001]}]
grid_search = GridSearchCV(estimator = svc,
                           param_grid = parameters,
                           scoring = 'accuracy',
                           n_jobs = -1)
grid_search = grid_search.fit(X_train, y_train)
best_accuracy = grid_search.best_score_
best_parameters = grid_search.best_params_
print("Best Accuracy: {:.2f} %".format(best_accuracy*100))
print("Best Parameters:", best_parameters)

svc_param=SVC(kernel='rbf',gamma=0.01,C=100,probability=True)
svc_param.fit(X_train,y_train)

import pickle
# Saving model to disk
pickle.dump(svc_param, open('model.pkl','wb'))

model=pickle.load(open('model.pkl','rb'))

Here is the project structure.

Here is the screenshot when i run the project into browser.

Answer 1

This is very likely to be a versioning problem. Your scikit-learn version is probably the latest version and the model.pkl you downloaded from the repo you mentioned is an old and incompatible version.

To avoid this kind of problem, we should stick to best practices such as using a requirements.txt file defining exactly the versions using during development. The same versions could then be installed on production.

If you really need to use this model.pkl from the repo, I'd suggest creating a GitHub issue asking for a requirement.txt file. Alternatively, you could try different scikit-learn versions until you get it working, but this can be very cumbersome.