# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
import seaborn as sns # plotting libraries
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report, precision_recall_curve, roc_curve
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import LinearSVC

#set style of sns
sns.set(style='whitegrid', color_codes=True)
sns.set(rc={'figure.figsize':(12,9)})

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

#load in the data and check out the first few rows
df = pd.read_csv('/kaggle/input/creditcardfraud/creditcard.csv')
df.head()

#first, get some info about the data - note, first run appears to be a complete dataset with no null values
print(df.info())
print(df.describe())

#Class = 1 when there is a fraud detected; so lets investigate the proportion of the total that is fraudulent, and also correlations
prop_fraud = df['Class'].sum()/len(df['Class'])
prop_fraud