机器学习项目实战(四) 心脏病发作预测

机器学习项目实战系列   心脏病发作预测

目录

机器学习项目实战系列   心脏病发作预测

一、概述

二、使用数据集

1.数据集Column

2.导入数据

3.查看唯一数据统计

4.汇总统计

5.分类汇总

6.相关性矩阵

​ 7.数据分布

---

一、概述

心脏病发作分类分析

心脏病发作数据集 https://www.kaggle.com/rashikrahmanpritom/heart-attack-analysis-prediction-dataset

---

二、使用数据集

1.数据集Column

age - Age of the patient

sex - Sex of the patient

cp - Chest pain type ~ 0 = Typical Angina, 1 = Atypical Angina, 2 = Non-anginal Pain, 3 = Asymptomatic

trtbps - Resting blood pressure (in mm Hg)

chol - Cholestoral in mg/dl fetched via BMI sensor

fbs - (fasting blood sugar > 120 mg/dl) ~ 1 = True, 0 = False

restecg - Resting electrocardiographic results ~ 0 = Normal, 1 = ST-T wave normality, 2 = Left ventricular hypertrophy

thalachh - Maximum heart rate achieved

oldpeak - Previous peak

slp - Slope

caa - Number of major vessels

thall - Thalium Stress Test result ~ (0,3)

exng - Exercise induced angina ~ 1 = Yes, 0 = No

output - Target variable

2.导入数据

3.查看唯一数据统计

4.汇总统计

5.分类汇总

fig = plt.figure(figsize=(18,15))
gs = fig.add_gridspec(3,3)
gs.update(wspace=0.5, hspace=0.25)
ax0 = fig.add_subplot(gs[0,0])
ax1 = fig.add_subplot(gs[0,1])
ax2 = fig.add_subplot(gs[0,2])
ax3 = fig.add_subplot(gs[1,0])
ax4 = fig.add_subplot(gs[1,1])
ax5 = fig.add_subplot(gs[1,2])
ax6 = fig.add_subplot(gs[2,0])
ax7 = fig.add_subplot(gs[2,1])
ax8 = fig.add_subplot(gs[2,2])

background_color = "#ffe6e6"
color_palette = ["#800000","#8000ff","#6aac90","#5833ff","#da8829"]
fig.patch.set_facecolor(background_color) 
ax0.set_facecolor(background_color) 
ax1.set_facecolor(background_color) 
ax2.set_facecolor(background_color) 
ax3.set_facecolor(background_color) 
ax4.set_facecolor(background_color) 
ax5.set_facecolor(background_color) 
ax6.set_facecolor(background_color) 
ax7.set_facecolor(background_color) 
ax8.set_facecolor(background_color) 

# Title of the plot
ax0.spines["bottom"].set_visible(False)
ax0.spines["left"].set_visible(False)
ax0.spines["top"].set_visible(False)
ax0.spines["right"].set_visible(False)
ax0.tick_params(left=False, bottom=False)
ax0.set_xticklabels([])
ax0.set_yticklabels([])
ax0.text(0.5,0.5,
         'Count plot for various\n categorical features\n_________________',
         horizontalalignment='center',
         verticalalignment='center',
         fontsize=18, fontweight='bold',
         fontfamily='serif',
         color="#000000")

# Sex count
ax1.text(0.3, 220, 'Sex', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax1.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax1,data=df,x='sex',palette=color_palette)
ax1.set_xlabel("")
ax1.set_ylabel("")

# Exng count
ax2.text(0.3, 220, 'Exng', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax2.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax2,data=df,x='exng',palette=color_palette)
ax2.set_xlabel("")
ax2.set_ylabel("")

# Caa count
ax3.text(1.5, 200, 'Caa', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax3.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax3,data=df,x='caa',palette=color_palette)
ax3.set_xlabel("")
ax3.set_ylabel("")

# Cp count
ax4.text(1.5, 162, 'Cp', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax4.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax4,data=df,x='cp',palette=color_palette)
ax4.set_xlabel("")
ax4.set_ylabel("")

# Fbs count
ax5.text(0.5, 290, 'Fbs', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax5.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax5,data=df,x='fbs',palette=color_palette)
ax5.set_xlabel("")
ax5.set_ylabel("")

# Restecg count
ax6.text(0.75, 165, 'Restecg', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax6.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax6,data=df,x='restecg',palette=color_palette)
ax6.set_xlabel("")
ax6.set_ylabel("")

# Slp count
ax7.text(0.85, 155, 'Slp', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax7.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax7,data=df,x='slp',palette=color_palette)
ax7.set_xlabel("")
ax7.set_ylabel("")

# Thall count
ax8.text(1.2, 180, 'Thall', fontsize=14, fontweight='bold', fontfamily='serif', color="#000000")
ax8.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.countplot(ax=ax8,data=df,x='thall',palette=color_palette)
ax8.set_xlabel("")
ax8.set_ylabel("")

for s in ["top","right","left"]:
    ax1.spines[s].set_visible(False)
    ax2.spines[s].set_visible(False)
    ax3.spines[s].set_visible(False)
    ax4.spines[s].set_visible(False)
    ax5.spines[s].set_visible(False)
    ax6.spines[s].set_visible(False)
    ax7.spines[s].set_visible(False)
    ax8.spines[s].set_visible(False)

6.相关性矩阵

fig = plt.figure(figsize=(12,12))
corr_mat = df.corr().stack().reset_index(name="correlation")
g = sns.relplot(
    data=corr_mat,
    x="level_0", y="level_1", hue="correlation", size="correlation",
    palette="YlGnBu", hue_norm=(-1, 1), edgecolor=".7",
    height=10, sizes=(50, 250), size_norm=(-.2, .8),
)
g.set(xlabel="features on X", ylabel="featurs on Y", aspect="equal")
g.fig.suptitle('Scatterplot heatmap',fontsize=22, fontweight='bold', fontfamily='serif', color="#000000")
g.despine(left=True, bottom=True)
g.ax.margins(.02)
for label in g.ax.get_xticklabels():
    label.set_rotation(90)
for artist in g.legend.legendHandles:
    artist.set_edgecolor(".7")
plt.show()

7.数据分布

fig = plt.figure(figsize=(18,18))
gs = fig.add_gridspec(5,2)
gs.update(wspace=0.5, hspace=0.5)
ax0 = fig.add_subplot(gs[0,0])
ax1 = fig.add_subplot(gs[0,1])
ax2 = fig.add_subplot(gs[1,0])
ax3 = fig.add_subplot(gs[1,1])
ax4 = fig.add_subplot(gs[2,0])
ax5 = fig.add_subplot(gs[2,1])
ax6 = fig.add_subplot(gs[3,0])
ax7 = fig.add_subplot(gs[3,1])
ax8 = fig.add_subplot(gs[4,0])
ax9 = fig.add_subplot(gs[4,1])

background_color = "#ffe6e6"
color_palette = ["#800000","#8000ff","#6aac90","#5833ff","#da8829"]
fig.patch.set_facecolor(background_color) 
ax0.set_facecolor(background_color) 
ax1.set_facecolor(background_color) 
ax2.set_facecolor(background_color)
ax3.set_facecolor(background_color)
ax4.set_facecolor(background_color)
ax5.set_facecolor(background_color) 
ax6.set_facecolor(background_color) 
ax7.set_facecolor(background_color)
ax8.set_facecolor(background_color)
ax9.set_facecolor(background_color)

# Age title
ax0.text(0.5,0.5,"Distribution of age\naccording to\n target variable\n___________",
        horizontalalignment = 'center',
        verticalalignment = 'center',
        fontsize = 18,
        fontweight='bold',
        fontfamily='serif',
        color='#000000')
ax0.spines["bottom"].set_visible(False)
ax0.set_xticklabels([])
ax0.set_yticklabels([])
ax0.tick_params(left=False, bottom=False)

# Age
ax1.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.kdeplot(ax=ax1, data=df, x='age',hue="output", fill=True,palette=["#8000ff","#da8829"], alpha=.5, linewidth=0)
ax1.set_xlabel("")
ax1.set_ylabel("")

# TrTbps title
ax2.text(0.5,0.5,"Distribution of trtbps\naccording to\n target variable\n___________",
        horizontalalignment = 'center',
        verticalalignment = 'center',
        fontsize = 18,
        fontweight='bold',
        fontfamily='serif',
        color='#000000')
ax2.spines["bottom"].set_visible(False)
ax2.set_xticklabels([])
ax2.set_yticklabels([])
ax2.tick_params(left=False, bottom=False)

# TrTbps
ax3.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.kdeplot(ax=ax3, data=df, x='trtbps',hue="output", fill=True,palette=["#8000ff","#da8829"], alpha=.5, linewidth=0)
ax3.set_xlabel("")
ax3.set_ylabel("")

# Chol title
ax4.text(0.5,0.5,"Distribution of chol\naccording to\n target variable\n___________",
        horizontalalignment = 'center',
        verticalalignment = 'center',
        fontsize = 18,
        fontweight='bold',
        fontfamily='serif',
        color='#000000')
ax4.spines["bottom"].set_visible(False)
ax4.set_xticklabels([])
ax4.set_yticklabels([])
ax4.tick_params(left=False, bottom=False)

# Chol
ax5.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.kdeplot(ax=ax5, data=df, x='chol',hue="output", fill=True,palette=["#8000ff","#da8829"], alpha=.5, linewidth=0)
ax5.set_xlabel("")
ax5.set_ylabel("")

# Thalachh title
ax6.text(0.5,0.5,"Distribution of thalachh\naccording to\n target variable\n___________",
        horizontalalignment = 'center',
        verticalalignment = 'center',
        fontsize = 18,
        fontweight='bold',
        fontfamily='serif',
        color='#000000')
ax6.spines["bottom"].set_visible(False)
ax6.set_xticklabels([])
ax6.set_yticklabels([])
ax6.tick_params(left=False, bottom=False)

# Thalachh
ax7.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.kdeplot(ax=ax7, data=df, x='thalachh',hue="output", fill=True,palette=["#8000ff","#da8829"], alpha=.5, linewidth=0)
ax7.set_xlabel("")
ax7.set_ylabel("")

# Oldpeak title
ax8.text(0.5,0.5,"Distribution of oldpeak\naccording to\n target variable\n___________",
        horizontalalignment = 'center',
        verticalalignment = 'center',
        fontsize = 18,
        fontweight='bold',
        fontfamily='serif',
        color='#000000')
ax8.spines["bottom"].set_visible(False)
ax8.set_xticklabels([])
ax8.set_yticklabels([])
ax8.tick_params(left=False, bottom=False)

# Oldpeak
ax9.grid(color='#000000', linestyle=':', axis='y', zorder=0,  dashes=(1,5))
sns.kdeplot(ax=ax9, data=df, x='oldpeak',hue="output", fill=True,palette=["#8000ff","#da8829"], alpha=.5, linewidth=0)
ax9.set_xlabel("")
ax9.set_ylabel("")

for i in ["top","left","right"]:
    ax0.spines[i].set_visible(False)
    ax1.spines[i].set_visible(False)
    ax2.spines[i].set_visible(False)
    ax3.spines[i].set_visible(False)
    ax4.spines[i].set_visible(False)
    ax5.spines[i].set_visible(False)
    ax6.spines[i].set_visible(False)
    ax7.spines[i].set_visible(False)
    ax8.spines[i].set_visible(False)
    ax9.spines[i].set_visible(False)