数据分析可视化复现

朴灿烈づ我的快乐病毒、 2022-03-20 10:14 309阅读 0赞

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

import warnings
    warnings.filterwarnings("ignore")

df = pd.read_csv("./data/HR.csv")

df = df[df["last_evaluation"]<=1][df["salary"]!="nme"][df["department"]!="sale"]

## 树状图 ##

sns.countplot(x="salary",data=df)

<matplotlib.axes._subplots.AxesSubplot at 0x1a1873c048>

![png][]

sns.countplot(x="salary",hue="department",data=df)

<matplotlib.axes._subplots.AxesSubplot at 0x1a182c0d30>

![png][png 1]

## 绘制直方图 ##

f = plt.figure()
    f.add_subplot(131)
    sns.distplot(df["satisfaction_level"],bins=10)

<matplotlib.axes._subplots.AxesSubplot at 0x1a17815748>

![png][png 2]

f = plt.figure()
    f.add_subplot(131)
    sns.distplot(df["satisfaction_level"],bins=10,kde=False)

<matplotlib.axes._subplots.AxesSubplot at 0x113840f98>

![png][png 3]

f = plt.figure()
    f.add_subplot(131)
    sns.distplot(df["satisfaction_level"],bins=10,hist=False)

<matplotlib.axes._subplots.AxesSubplot at 0x1a17c3e9b0>

![png][png 4]

f = plt.figure()
    f.add_subplot(131)
    sns.distplot(df["satisfaction_level"],bins=10)
    f.add_subplot(132)
    sns.distplot(df["last_evaluation"],bins=10)
    f.add_subplot(133)
    sns.distplot(df["average_monthly_hours"],bins=10)

<matplotlib.axes._subplots.AxesSubplot at 0x1a17d31160>

![png][png 5]

## 箱线图 ##

sns.boxplot(y=df["time_spend_company"])

<matplotlib.axes._subplots.AxesSubplot at 0x1a17f06128>

![png][png 6]

sns.boxplot(x=df["time_spend_company"],saturation=0.75,whis=3)

<matplotlib.axes._subplots.AxesSubplot at 0x1a18e94b70>

![png][png 7]

## 折线图 ##

sub_df = df.groupby("time_spend_company").mean()

sns.pointplot(sub_df.index,sub_df["left"])

<matplotlib.axes._subplots.AxesSubplot at 0x1a19e08208>

![png][png 8]

sns.pointplot(x="time_spend_company",y="left",data=df)

<matplotlib.axes._subplots.AxesSubplot at 0x1a1919c6d8>

![png][png 9]

lbs = df["department"].value_counts().index
    plt.pie(df["department"].value_counts(normalize=True),labels=lbs,autopct="%1.1f%%")
    plt.show()

![png][png 10]

lbs = df["department"].value_counts().index 
    explodes=[0.1 if i=="sales" else 0 for i in lbs]
    plt.pie(df["department"].value_counts(normalize=True),explode=explodes,labels=lbs,autopct="%1.1f%%")
    plt.show()

![png][png 11]

lbs = df["salary"].value_counts().index 
    explodes=[0.1 if i=="low" else 0 for i in lbs]
    plt.pie(df["salary"].value_counts(normalize=True),explode=explodes,labels=lbs,autopct="%1.1f%%")
    plt.show()

![png][png 12]

[png]: /images/20220320/fd5fd9e132d440df9f7bf54af35f65d8.png
[png 1]: /images/20220320/01876a5f2bff4a3eb868d915c36a2914.png
[png 2]: /images/20220320/4fdc9d37424a43ee8d42d9c5565b3449.png
[png 3]: /images/20220320/b39b252aad96416ab504b7b8a5a730be.png
[png 4]: /images/20220320/962fa45c8c7d4be78f7758e6dae1e3c3.png
[png 5]: /images/20220320/a071550e96144bc6a2a736d38e4c9c27.png
[png 6]: /images/20220320/3ef3b8d22d7f45cfa2fe936d6701f77c.png
[png 7]: /images/20220320/7c8f61dee40343599574a1adc12796d7.png
[png 8]: /images/20220320/bc8ac1def99c44c18ea85f472de72891.png
[png 9]: /images/20220320/a61c1d87d000427d97a2816b0ca515e9.png
[png 10]: /images/20220320/f935e53de85249089a1f10b80e85430b.png
[png 11]: /images/20220320/01f89e779a6543eba68c4167d14d0b03.png
[png 12]: /images/20220320/8360e476aa674b9e83a2f92c870127d4.png