Proyecto #StartupReady: Análisis Exploratorio de Datos

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns # agrega librerías que necesites

url_wine_red = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv' url_wine_white = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv'

red = pd.read_csv(url_wine_red, delimiter=';') white = pd.read_csv(url_wine_white, delimiter=';')

red.head()

fixed acidityfloat64

volatile acidityfloat64

7.4

0.7

7.8

0.88

7.8

0.76

11.2

0.28

7.4

0.7

white.head()

fixed acidityfloat64

volatile acidityfloat64

0.27

6.3

0.3

8.1

0.28

7.2

0.23

7.2

0.23

red['category']='red' white['category']='white'

total_wine=red.append(white, ignore_index=True)

total_wine.head()

fixed acidityfloat64

volatile acidityfloat64

7.4

0.7

7.8

0.88

7.8

0.76

11.2

0.28

7.4

0.7

total_wine.shape

total_wine.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6497 entries, 0 to 6496
Data columns (total 13 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   fixed acidity         6497 non-null   float64
 1   volatile acidity      6497 non-null   float64
 2   citric acid           6497 non-null   float64
 3   residual sugar        6497 non-null   float64
 4   chlorides             6497 non-null   float64
 5   free sulfur dioxide   6497 non-null   float64
 6   total sulfur dioxide  6497 non-null   float64
 7   density               6497 non-null   float64
 8   pH                    6497 non-null   float64
 9   sulphates             6497 non-null   float64
 10  alcohol               6497 non-null   float64
 11  quality               6497 non-null   int64  
 12  category              6497 non-null   object 
dtypes: float64(11), int64(1), object(1)
memory usage: 660.0+ KB

total_wine.describe()

fixed acidityfloat64

volatile acidityfloat64

count

6497

mean

7.215307064799139

0.3396659996921656

std

1.2964337577998153

0.16463647408467877

min

3.8

0.08

25%

6.4

0.23

50%

0.29

75%

7.7

0.4

max

15.9

1.58

quality = total_wine['quality'] quality

sns.histplot(quality)

sns.countplot(data= total_wine, x= quality )

total_wine['quality_category'] = total_wine['quality'].apply(lambda x: "Poor" if x < 5 else ("Medium " if x >=5 and x <= 7 else "High")) total_wine.tail()

fixed acidityfloat64

volatile acidityfloat64

6492

6.2

0.21

6493

6.6

0.32

6494

6.5

0.24

6495

5.5

0.29

6496

0.21

total_wine.quality_category = total_wine['quality_category'].astype('category') total_wine.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6497 entries, 0 to 6496
Data columns (total 14 columns):
 #   Column                Non-Null Count  Dtype   
---  ------                --------------  -----   
 0   fixed acidity         6497 non-null   float64 
 1   volatile acidity      6497 non-null   float64 
 2   citric acid           6497 non-null   float64 
 3   residual sugar        6497 non-null   float64 
 4   chlorides             6497 non-null   float64 
 5   free sulfur dioxide   6497 non-null   float64 
 6   total sulfur dioxide  6497 non-null   float64 
 7   density               6497 non-null   float64 
 8   pH                    6497 non-null   float64 
 9   sulphates             6497 non-null   float64 
 10  alcohol               6497 non-null   float64 
 11  quality               6497 non-null   int64   
 12  category              6497 non-null   object  
 13  quality_category      6497 non-null   category
dtypes: category(1), float64(11), int64(1), object(1)
memory usage: 666.5+ KB

sns.countplot(total_wine['quality_category'])

/shared-libs/python3.7/py/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

sns.boxplot(quality)

wine_corr = total_wine.corr() wine_corr

fixed acidityfloat64

-0.32905390129521767 - 1.0

volatile acidityfloat64

-0.41447619465071844 - 1.0

fixed acidity

0.21900825635099574

volatile acidity

0.21900825635099574

citric acid

0.32443572544729976

-0.3779813170552629

residual sugar

-0.11198128107823482

-0.19601117434765578

chlorides

0.2981947717027338

0.3771242764338664

free sulfur dioxide

-0.2827354283695625

-0.35255730641340643

total sulfur dioxide

-0.32905390129521767

-0.41447619465071844

density

0.45890998228056823

0.2712956478513891

-0.2527004683162197

0.2614544027422696

sulphates

0.29956774438249295

0.22598367974107575

plt.figure(figsize =(10,10)) sns.heatmap(wine_corr, annot= True, cmap='PuBu')

totoal_wine_sort = total_wine.corr()[['quality']].sort_values(by='quality', ascending = False) totoal_wine_sort

qualityfloat64

-0.3058579060694202 - 1.0

density

-0.3058579060694202

volatile acidity

-0.2656994776114667

chlorides

-0.20066550043510237

fixed acidity

-0.07674320790961939

total sulfur dioxide

-0.041385453855609024

residual sugar

-0.036980484585769566

0.01950570371443272

sulphates

0.03848544587651378

free sulfur dioxide

0.055463058616633

citric acid

0.08553171718367873

sns.pairplot(total_wine, x_vars=["density", "volatile acidity", "chlorides"], y_vars=["alcohol", "citric acid"], hue= 'quality', kind = 'scatter');

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.barplot(data=total_wine, x= 'quality_category', y= 'density',ax = ax1) ax1.set_ylim(0.98,1.05) sns.violinplot(data=total_wine, x= 'quality_category', y= 'density', ax = ax2) ax2.set_ylim(0.98,1.05) fig.tight_layout()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.barplot(data=total_wine, x= 'quality_category', y= 'volatile acidity', ax = ax1) ax1.set_ylim(-0.14, 1.83) sns.violinplot(data=total_wine, x= 'quality_category', y= 'volatile acidity', ax = ax2) ax2.set_ylim(-0.14, 1.83) fig.tight_layout()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.barplot(data=total_wine, x= 'quality_category', y= 'chlorides', ax = ax1) ax1.set_ylim(-0.05, 0.675) sns.violinplot(data=total_wine, x= 'quality_category', y= 'chlorides', ax = ax2) ax2.set_ylim(-0.05, 0.675) fig.tight_layout()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.barplot(data=total_wine, x= 'quality_category', y= 'alcohol', ax = ax1) ax1.set_ylim(6.93,15.71) sns.violinplot(data=total_wine, x= 'quality_category', y= 'alcohol', ax = ax2) ax2.set_ylim(6.93,15.71) fig.tight_layout()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.barplot(data=total_wine, x= 'quality_category', y= 'citric acid', ax = ax1) ax1.set_ylim(-0.21, 1.80) sns.violinplot(data=total_wine, x= 'quality_category', y= 'citric acid', ax = ax2) fig.tight_layout()