school = 'Platzi'
# print(____) # Incluir la variable declarada anteriormente.
print(school)
Platzi
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(5)
fixed acidityfloat64
volatile acidityfloat64
0
7.4
0.7
1
7.8
0.88
2
7.8
0.76
3
11.2
0.28
4
7.4
0.7
white.head(5)
fixed acidityfloat64
volatile acidityfloat64
0
7
0.27
1
6.3
0.3
2
8.1
0.28
3
7.2
0.23
4
7.2
0.23
red['Category']='red'
white['Category']='white'
# total_wine=red.merge(white, ignore_index=True)
total_wine=pd.concat([red, white], ignore_index=True)
total_wine.head(5)
fixed acidityfloat64
volatile acidityfloat64
0
7.4
0.7
1
7.8
0.88
2
7.8
0.76
3
11.2
0.28
4
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
6497
mean
7.215307065
0.3396659997
std
1.296433758
0.1646364741
min
3.8
0.08
25%
6.4
0.23
50%
7
0.29
75%
7.7
0.4
max
15.9
1.58
quality = total_wine['quality']
quality.describe()
quality.value_counts()
sns.set_theme(style="darkgrid")
sns.countplot(data=total_wine, y='quality')
plt.show()
total_wine['quality_category'] = total_wine['quality'].apply(lambda x: str('Poor') if x <= 5 else (str('High') if x >=7 else str('Medium')))
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
6
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="dark")
sns.countplot(data=total_wine, y='quality_category')
plt.xlabel('Wine')
plt.ylabel('Quality')
plt.show()
high = len(quality[(quality >= 7)])
por_high = round(high * 100 / len(quality.index))
medium = len(quality[(quality == 6)])
por_medium = round(medium * 100 / len(quality.index))
print('Los vinos de alta calidad solamente representan un',por_high,'% del total.\nMientras que la mayoría son los de calidad media con su',por_medium,'%')
Los vinos de alta calidad solamente representan un 20 % del total.
Mientras que la mayoría son los de calidad media con su 44 %
# Desviación estándar
quality.std()
# Rango
rango = quality.max() - quality.min()
rango
# Quartiles
median = quality.median()
q1 = quality.quantile(q=0.25)
q3 = quality.quantile(q=0.75)
min_val = quality.quantile(q=0)
max_val = quality.quantile(q=1)
# out_max = len(quality[(quality > 7)])
#out_min = len(quality[(quality < 4)])
#print(out_max + out_min)
print(min_val, q1, median, q3, max_val)
3.0 5.0 6.0 6.0 9.0
# Rango Intercuartil
iqr = q3 - q1
iqr
# Datos simétricamente distribuidos
minlimit = q1 - 1.5*iqr
maxlimit = q3 + 1.5*iqr
print(minlimit, maxlimit)
3.5 7.5
plt.hist(quality, bins=5, histtype='bar')
plt.ylabel('Wine')
plt.xlabel('Quality')
plt.show()
plt.figure(figsize=(8,4))
sns.boxplot(data=total_wine, x='quality')
plt.axvline(quality.median(), color='magenta', label='median', linestyle='-')
plt.axvline(quality.mean(), color='orange', label='mean', linestyle='--')
plt.legend()
plt.show()
out_max = len(quality[(quality > 7)])
out_min = len(quality[(quality < 4)])
out = out_max + out_min
outpor = round(out * 100 / len(quality.index))
print('Hay',out, 'valores atípicos, el', outpor,'% del total')
Hay 228 valores atípicos, el 4 % del total
# 3. Elimina los outliers de ser necesario en la siguiente celda.
print('No :v')
No :v
total_wine.corr()
fixed acidityfloat64
-0.32905390129521767 - 1.0
volatile acidityfloat64
-0.41447619465071844 - 1.0
fixed acidity
1
0.2190082564
volatile acidity
0.2190082564
1
citric acid
0.3244357254
-0.3779813171
residual sugar
-0.1119812811
-0.1960111743
chlorides
0.2981947717
0.3771242764
free sulfur dioxide
-0.2827354284
-0.3525573064
total sulfur dioxide
-0.3290539013
-0.4144761947
density
0.4589099823
0.2712956479
pH
-0.2527004683
0.2614544027
sulphates
0.2995677444
0.2259836797
alcohol
-0.09545152256
-0.03764038584
quality
-0.07674320791
-0.2656994776
plt.figure(figsize=(16,16))
sns.heatmap(total_wine.corr(), annot=True, cmap='coolwarm', linewidths=5, linecolor='aquamarine',
vmin=-0.5, vmax=0.5)
plt.show()
total_wine.corr()[['quality']].sort_values(by='quality', ascending = False)
qualityfloat64
-0.3058579060694202 - 1.0
quality
1
alcohol
0.44431852
citric acid
0.08553171718
free sulfur dioxide
0.05546305862
sulphates
0.03848544588
pH
0.01950570371
residual sugar
-0.03698048459
total sulfur dioxide
-0.04138545386
fixed acidity
-0.07674320791
chlorides
-0.2006655004
volatile acidity
-0.2656994776
density
-0.3058579061
# total_wine.columns
wine_corr = total_wine.drop(['quality', 'fixed acidity', 'citric acid', 'residual sugar', 'free sulfur dioxide', 'total sulfur dioxide', 'pH', 'sulphates'], axis=1)
sns.heatmap(wine_corr.corr(), annot=True, cmap='Spectral', linewidths=2, linecolor='indigo',
vmin=-0.5, vmax=0.5)
plt.show()
# Alcohol vs Calidad
f, axs = plt.subplots(1, 2, figsize=(8, 4), gridspec_kw=dict(width_ratios=[4, 3]))
sns.set(style='darkgrid',palette='deep',font_scale=1)
sns.barplot(data=total_wine, x='quality_category', y='alcohol', ax=axs[0])
sns.violinplot(data=total_wine, x='quality_category', y='alcohol', ax=axs[1])
f.tight_layout()
# Sal vs Calidad
f, axs = plt.subplots(1, 2, figsize=(8, 4), gridspec_kw=dict(width_ratios=[4, 3]))
sns.set(style='darkgrid',palette='deep',font_scale=1)
sns.barplot(data=total_wine, x='quality_category', y='chlorides', ax=axs[0])
sns.violinplot(data=total_wine, x='quality_category', y='chlorides', ax=axs[1])
f.tight_layout()
# ácido acético
f, axs = plt.subplots(1, 2, figsize=(8, 4), gridspec_kw=dict(width_ratios=[4, 3]))
sns.set(style=