Updated 4 years ago
# 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)
# 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 20GB 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
/kaggle/input/quant-ori/Quantmetry.csv
import os
import sys
import operator
import numpy as np
import pandas as pd
import scipy
from scipy import sparse
from sklearn import model_selection, preprocessing, ensemble
from sklearn.metrics import log_loss
import re
'''Plotly visualization .'''
import matplotlib.pyplot as plt
import seaborn as sns
color = sns.color_palette()
%matplotlib inline
import plotly.offline as py
import plotly.graph_objs as go
import plotly.tools as tls
py.init_notebook_mode(connected=True)
'''Display markdown formatted output like bold, italic bold etc.'''
from IPython.display import Markdown
def bold(string):
display(Markdown(string))
'''Ignore deprecation and future, and user warnings.'''
import warnings as wrn
wrn.filterwarnings('ignore', category = DeprecationWarning)
wrn.filterwarnings('ignore', category = FutureWarning)
wrn.filterwarnings('ignore', category = UserWarning)
file ="../input/quant-ori/Quantmetry.csv"
df = pd.read_csv(file)
df.head()
#Variable Description
def description(df):
print(f"Dataset Shape: {df.shape}")
summary = pd.DataFrame(df.dtypes,columns=['dtypes'])
summary = summary.reset_index()
summary['Name'] = summary['index']
summary = summary[['Name','dtypes']]
summary['Missing'] = df.isnull().sum().values
summary['Uniques'] = df.nunique().values
summary['First Value'] = df.iloc[0].values
summary['Second Value'] = df.iloc[1].values
summary['Third Value'] = df.iloc[2].values
return summary
description(df)
Dataset Shape: (20000, 13)