dipanjanS

# -*- coding: utf-8 -*-
"""
Created on Sat Jun 07 11:11:16 2014

@author: Dipanjan
"""


#import sys
#from lxml import html

dipanjanS

Get the processor core affinity for a process ( cores on which it is allowed to run )

taskset -cp <PID>

Example,

[root@user]# taskset -cp 74515
pid 74515's current affinity list: 0-7

dipanjanS

white_wine = pd.read_csv('winequality-white.csv', sep=';')
red_wine = pd.read_csv('winequality-red.csv', sep=';')

# store wine type as an attribute
red_wine['wine_type'] = 'red'   
white_wine['wine_type'] = 'white'

# bucket wine quality scores into qualitative quality labels
red_wine['quality_label'] = red_wine['quality'].apply(lambda value: 'low' 
                                                          if value <= 5 else 'medium' 

dipanjanS

subset_attributes = ['residual sugar', 'total sulfur dioxide', 'sulphates', 
                     'alcohol', 'volatile acidity', 'quality']
rs = round(red_wine[subset_attributes].describe(),2)
ws = round(white_wine[subset_attributes].describe(),2)

pd.concat([rs, ws], axis=1, keys=['Red Wine Statistics', 'White Wine Statistics'])

dipanjanS

wines.hist(bins=15, color='steelblue', edgecolor='black', linewidth=1.0,
           xlabelsize=8, ylabelsize=8, grid=False)    
plt.tight_layout(rect=(0, 0, 1.2, 1.2))   

dipanjanS

# Histogram
fig = plt.figure(figsize = (6,4))
title = fig.suptitle("Sulphates Content in Wine", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)

ax = fig.add_subplot(1,1, 1)
ax.set_xlabel("Sulphates")
ax.set_ylabel("Frequency") 
ax.text(1.2, 800, r'$\mu$='+str(round(wines['sulphates'].mean(),2)), 
         fontsize=12)

dipanjanS

# Bar Plot
fig = plt.figure(figsize = (6, 4))
title = fig.suptitle("Wine Quality Frequency", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)

ax = fig.add_subplot(1,1, 1)
ax.set_xlabel("Quality")
ax.set_ylabel("Frequency") 
w_q = wines['quality'].value_counts()
w_q = (list(w_q.index), list(w_q.values))

dipanjanS

# Correlation Matrix Heatmap
f, ax = plt.subplots(figsize=(10, 6))
corr = wines.corr()
hm = sns.heatmap(round(corr,2), annot=True, ax=ax, cmap="coolwarm",fmt='.2f',
                 linewidths=.05)
f.subplots_adjust(top=0.93)
t= f.suptitle('Wine Attributes Correlation Heatmap', fontsize=14)

dipanjanS

# Pair-wise Scatter Plots
cols = ['density', 'residual sugar', 'total sulfur dioxide', 'fixed acidity']
pp = sns.pairplot(wines[cols], size=1.8, aspect=1.8,
                  plot_kws=dict(edgecolor="k", linewidth=0.5),
                  diag_kind="kde", diag_kws=dict(shade=True))

fig = pp.fig 
fig.subplots_adjust(top=0.93, wspace=0.3)
t = fig.suptitle('Wine Attributes Pairwise Plots', fontsize=14)

dipanjanS

# Scaling attribute values to avoid few outiers
cols = ['density', 'residual sugar', 'total sulfur dioxide', 'fixed acidity']
subset_df = wines[cols]

from sklearn.preprocessing import StandardScaler
ss = StandardScaler()

scaled_df = ss.fit_transform(subset_df)
scaled_df = pd.DataFrame(scaled_df, columns=cols)
final_df = pd.concat([scaled_df, wines['wine_type']], axis=1)