Proyecto: Análisis Exploratorio de Datos

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns

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(5)

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(5)

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(5)

fixed acidityfloat64

volatile acidityfloat64

7.4

0.7

7.8

0.88

7.8

0.76

11.2

0.28

7.4

0.7

This chart is empty

np.shape(total_wine) print("N° de Filas: " + str(total_wine.shape[0])) print("N° de Columnas: " + str(total_wine.shape[1]))

N° de Filas: 6497
N° de Columnas: 13

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_analysis = total_wine['quality'] quality_analysis.describe()

total_wine.groupby('quality').count()

fixed acidityint64

volatile acidityint64

216

2138

2836

1079

193

sns.set_theme(style='darkgrid') sns.countplot(total_wine['quality']) plt.show()

/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

total_wine['quality_category'] = total_wine['quality'].apply(lambda x: 'Poor' if x<=3 else ('Medium' if x<=6 else 'Hihg')) 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.set_theme(style='darkgrid') sns.catplot(x="quality_category", col="category", kind="count", data=total_wine) plt.show()

figure = plt.figure(figsize=(20,13)) cols = ['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar', 'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density', 'pH', 'sulphates', 'alcohol', 'quality'] count = 1 for col in cols: figure.add_subplot(3,4,count) sns.boxplot(total_wine[col]) count += 1 plt.show()

/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
/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
/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
/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
/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
/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
/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
/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
/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
/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
/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
/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

matrix_corr = total_wine.corr(method='spearman') matrix_corr.head(12)

fixed acidityfloat64

-0.259914181930563 - 1.0

volatile acidityfloat64

-0.36567327125402044 - 1.0

fixed acidity

0.20027175377938752

volatile acidity

0.20027175377938752

citric acid

0.2705679150280851

-0.2951287387426284

residual sugar

-0.03225370199223037

-0.06438414511931495

chlorides

0.3559641185159034

0.4158958312664764

free sulfur dioxide

-0.259914181930563

-0.36567327125402044

total sulfur dioxide

-0.23325862146001403

-0.343534200145776

density

0.4340562148199566

0.26143698981126734

-0.25004402556806243

0.19487560523346154

sulphates

0.22014500369929912

0.2550419991498638

plt.figure(figsize=(20,12)) sns.heatmap(matrix_corr, xticklabels=matrix_corr.columns, yticklabels=matrix_corr.columns, center=0, annot=True) plt.show()

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

qualityfloat64

-0.3058579060694202 - 1.0

quality

alcohol

0.4443185200076552

citric acid

0.08553171718367873

free sulfur dioxide

0.055463058616633

sulphates

0.03848544587651378

0.01950570371443272

residual sugar

-0.036980484585769566

total sulfur dioxide

-0.041385453855609024

fixed acidity

-0.07674320790961939

chlorides

-0.20066550043510237

total_wine_mini = total_wine[['alcohol','density','chlorides','volatile acidity','quality', 'quality_category']] total_wine_mini.head()

alcoholfloat64

densityfloat64

9.4

0.9978

9.8

0.9968

9.8

0.997

9.8

0.998

9.4

0.9978

total_wine_miniCorr = total_wine_mini.corr() total_wine_miniCorr

alcoholfloat64

densityfloat64

alcohol

-0.6867454216820776

density

-0.6867454216820776

chlorides

-0.25691557997343767

0.3626146565579579

volatile acidity

-0.03764038583873583

0.27129564785138865

quality

0.4443185200076552

-0.3058579060694202

sns.set(rc={'figure.figsize':(12,7)}) sns.heatmap(data=total_wine_miniCorr,annot=True) sns.set_theme(style='ticks') plt.show()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.set_theme(style='darkgrid') sns.barplot(data=total_wine, x= 'quality_category', y= 'alcohol',ax = ax1) ax1.set_ylim(0,20) sns.violinplot(data=total_wine, x= 'quality_category', y= 'alcohol', ax = ax2) ax2.set_ylim(6,18) plt.show()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.set_theme(style='darkgrid') sns.barplot(data=total_wine, x= 'quality_category', y= 'density',ax = ax1) ax1.set_ylim(0,2.5) sns.violinplot(data=total_wine, x= 'quality_category', y= 'density', ax = ax2) ax2.set_ylim(0.98,1.05) plt.show()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.set_theme(style='darkgrid') sns.barplot(data=total_wine, x= 'quality_category', y= 'chlorides',ax = ax1) ax1.set_ylim(0,0.18) sns.violinplot(data=total_wine, x= 'quality_category', y= 'chlorides', ax = ax2) ax2.set_ylim(-0.1,0.7) plt.show()

fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) sns.set_theme(style='darkgrid') sns.barplot(data=total_wine, x= 'quality_category', y= 'volatile acidity',ax = ax1) ax1.set_ylim(0,1.4) sns.violinplot(data=total_wine, x= 'quality_category', y= 'volatile acidity', ax = ax2) ax2.set_ylim(-0.5,2.5) plt.show()