吴裕雄--天生自然 python数据分析：医疗费数据分析

灰太狼 2021-11-05 10:34 301阅读 0赞

![1020928-20190724164048886-953136835.png][]

import numpy as np 
    import pandas as pd 
    import os
    import matplotlib.pyplot as pl
    import seaborn as sns
    import warnings
    warnings.filterwarnings('ignore')
    data = pd.read_csv('F:\\kaggleDataSet\\MedicalCostPersonal\\insurance.csv')

data.head()

![1020928-20190724164322968-1601900515.png][]

data.isnull().sum()

![1020928-20190724164352385-1095655085.png][]

from sklearn.preprocessing import LabelEncoder
    #sex
    le = LabelEncoder()
    le.fit(data.sex.drop_duplicates()) 
    data.sex = le.transform(data.sex)
    # smoker or not
    le.fit(data.smoker.drop_duplicates()) 
    data.smoker = le.transform(data.smoker)
    #region
    le.fit(data.region.drop_duplicates()) 
    data.region = le.transform(data.region)

data.corr()['charges'].sort_values()

![1020928-20190724164435977-420745969.png][]

f, ax = pl.subplots(figsize=(10, 8))
    corr = data.corr()
    sns.heatmap(corr, mask=np.zeros_like(corr, dtype=np.bool), cmap=sns.diverging_palette(240,10,as_cmap=True),square=True, ax=ax)

![1020928-20190724164507422-1621484615.png][]

from bokeh.io import output_notebook, show
    from bokeh.plotting import figure
    output_notebook()
    import scipy.special
    from bokeh.layouts import gridplot
    from bokeh.plotting import figure, show, output_file
    p = figure(title="Distribution of charges",tools="save",background_fill_color="#E8DDCB")
    hist, edges = np.histogram(data.charges)
    p.quad(top=hist, bottom=0, left=edges[:-1], right=edges[1:],fill_color="#036564", line_color="#033649")
    p.xaxis.axis_label = 'x'
    p.yaxis.axis_label = 'Pr(x)'
    show(gridplot(p,ncols = 2, plot_width=400, plot_height=400, toolbar_location=None))

![1020928-20190724165428216-1234011502.png][]

f= pl.figure(figsize=(12,5))
    
    ax=f.add_subplot(121)
    sns.distplot(data[(data.smoker == 1)]["charges"],color='c',ax=ax)
    ax.set_title('Distribution of charges for smokers')
    
    ax=f.add_subplot(122)
    sns.distplot(data[(data.smoker == 0)]['charges'],color='b',ax=ax)
    ax.set_title('Distribution of charges for non-smokers')

![1020928-20190724165459876-615645353.png][]

sns.catplot(x="smoker", kind="count",hue = 'sex', palette="pink", data=data)

![1020928-20190724165526456-1636096364.png][]

sns.catplot(x="sex", y="charges", hue="smoker",kind="violin", data=data, palette = 'magma')

![1020928-20190724165559322-1269735186.png][]

pl.figure(figsize=(12,5))
    pl.title("Box plot for charges of women")
    sns.boxplot(y="smoker", x="charges", data =  data[(data.sex == 1)] , orient="h", palette = 'magma')

![1020928-20190724165630956-415737578.png][]

pl.figure(figsize=(12,5))
    pl.title("Box plot for charges of men")
    sns.boxplot(y="smoker", x="charges", data =  data[(data.sex == 0)] , orient="h", palette = 'rainbow')

![1020928-20190724165708728-992419485.png][]

pl.figure(figsize=(12,5))
    pl.title("Distribution of age")
    ax = sns.distplot(data["age"], color = 'g')

![1020928-20190724165741307-1775117322.png][]

sns.catplot(x="smoker", kind="count",hue = 'sex', palette="rainbow", data=data[(data.age == 18)])
    pl.title("The number of smokers and non-smokers (18 years old)")

![1020928-20190724165815030-1279158485.png][]

![1020928-20190724165836814-2011194405.png][]

g = sns.jointplot(x="age", y="charges", data = data[(data.smoker == 0)],kind="kde", color="m")
    g.plot_joint(pl.scatter, c="w", s=30, linewidth=1, marker="+")
    g.ax_joint.collections[0].set_alpha(0)
    g.set_axis_labels("$X$", "$Y$")
    ax.set_title('Distribution of charges and age for non-smokers')

![1020928-20190724165908551-456441605.png][]

g = sns.jointplot(x="age", y="charges", data = data[(data.smoker == 1)],kind="kde", color="c")
    g.plot_joint(pl.scatter, c="w", s=30, linewidth=1, marker="+")
    g.ax_joint.collections[0].set_alpha(0)
    g.set_axis_labels("$X$", "$Y$")
    ax.set_title('Distribution of charges and age for smokers')

![1020928-20190724165944518-211266543.png][]

#non - smokers
    p = figure(plot_width=500, plot_height=450)
    p.circle(x=data[(data.smoker == 0)].age,y=data[(data.smoker == 0)].charges, size=7, line_color="navy", fill_color="pink", fill_alpha=0.9)
    
    show(p)

![1020928-20190724170017305-1243557085.png][]

![1020928-20190724170050403-1134644492.png][]

#smokers
    p = figure(plot_width=500, plot_height=450)
    p.circle(x=data[(data.smoker == 1)].age,y=data[(data.smoker == 1)].charges, size=7, line_color="navy", fill_color="red", fill_alpha=0.9)
    show(p)

![1020928-20190724170126315-851146659.png][]

![1020928-20190724170203922-1539483470.png][]

sns.lmplot(x="age", y="charges", hue="smoker", data=data, palette = 'inferno_r', size = 7)
    ax.set_title('Smokers and non-smokers')

![1020928-20190724170234295-572526910.png][]

pl.figure(figsize=(12,5))
    pl.title("Distribution of bmi")
    ax = sns.distplot(data["bmi"], color = 'm')

![1020928-20190724170302901-228557936.png][]

pl.figure(figsize=(12,5))
    pl.title("Distribution of charges for patients with BMI greater than 30")
    ax = sns.distplot(data[(data.bmi >= 30)]['charges'], color = 'm')

![1020928-20190724170329583-1697755483.png][]

pl.figure(figsize=(12,5))
    pl.title("Distribution of charges for patients with BMI less than 30")
    ax = sns.distplot(data[(data.bmi < 30)]['charges'], color = 'b')

![1020928-20190724170357115-1453359752.png][]

g = sns.jointplot(x="bmi", y="charges", data = data,kind="kde", color="r")
    g.plot_joint(pl.scatter, c="w", s=30, linewidth=1, marker="+")
    g.ax_joint.collections[0].set_alpha(0)
    g.set_axis_labels("$X$", "$Y$")
    ax.set_title('Distribution of bmi and charges')

![1020928-20190724170422109-40253302.png][]

pl.figure(figsize=(10,6))
    ax = sns.scatterplot(x='bmi',y='charges',data=data,palette='magma',hue='smoker')
    ax.set_title('Scatter plot of charges and bmi')
    
    sns.lmplot(x="bmi", y="charges", hue="smoker", data=data, palette = 'magma', size = 8)

![1020928-20190724170459357-152223509.png][]

![1020928-20190724170515170-1221221095.png][]

sns.catplot(x="children", kind="count", palette="ch:.25", data=data, size = 6)

![1020928-20190724170540942-1249556108.png][]

sns.catplot(x="smoker", kind="count", palette="rainbow",hue = "sex",
                data=data[(data.children > 0)], size = 6)
    ax.set_title('Smokers and non-smokers who have childrens')

![1020928-20190724170626935-67862072.png][]

from sklearn.linear_model import LinearRegression
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import PolynomialFeatures
    from sklearn.metrics import r2_score,mean_squared_error
    from sklearn.ensemble import RandomForestRegressor

x = data.drop(['charges'], axis = 1)
    y = data.charges
    
    x_train,x_test,y_train,y_test = train_test_split(x,y, random_state = 0)
    lr = LinearRegression().fit(x_train,y_train)
    
    y_train_pred = lr.predict(x_train)
    y_test_pred = lr.predict(x_test)
    
    print(lr.score(x_test,y_test))

![1020928-20190724170714930-509594391.png][]

X = data.drop(['charges','region'], axis = 1)
    Y = data.charges
    
    quad = PolynomialFeatures (degree = 2)
    x_quad = quad.fit_transform(X)
    
    X_train,X_test,Y_train,Y_test = train_test_split(x_quad,Y, random_state = 0)
    
    plr = LinearRegression().fit(X_train,Y_train)
    
    Y_train_pred = plr.predict(X_train)
    Y_test_pred = plr.predict(X_test)
    
    print(plr.score(X_test,Y_test))

![1020928-20190724170746738-1878210397.png][]

forest = RandomForestRegressor(n_estimators = 100,criterion = 'mse',random_state = 1,n_jobs = -1)
    forest.fit(x_train,y_train)
    forest_train_pred = forest.predict(x_train)
    forest_test_pred = forest.predict(x_test)
    
    print('MSE train data: %.3f, MSE test data: %.3f' % (
    mean_squared_error(y_train,forest_train_pred),
    mean_squared_error(y_test,forest_test_pred)))
    print('R2 train data: %.3f, R2 test data: %.3f' % (
    r2_score(y_train,forest_train_pred),
    r2_score(y_test,forest_test_pred)))

![1020928-20190724170835283-1891431769.png][]

pl.figure(figsize=(10,6))
    
    pl.scatter(forest_train_pred,forest_train_pred - y_train,c = 'black', marker = 'o', s = 35, alpha = 0.5,label = 'Train data')
    pl.scatter(forest_test_pred,forest_test_pred - y_test,c = 'c', marker = 'o', s = 35, alpha = 0.7,label = 'Test data')
    pl.xlabel('Predicted values')
    pl.ylabel('Tailings')
    pl.legend(loc = 'upper left')
    pl.hlines(y = 0, xmin = 0, xmax = 60000, lw = 2, color = 'red')
    pl.show()

![1020928-20190724170917711-1252248179.png][]

转载于:https://www.cnblogs.com/tszr/p/11239352.html

[1020928-20190724164048886-953136835.png]: /images/20211104/aa7430b71aca4fa5a62e332eeae6eb52.png
[1020928-20190724164322968-1601900515.png]: /images/20211104/2eda7b419bfd445f9f00192176fb402e.png
[1020928-20190724164352385-1095655085.png]: /images/20211104/349b3c971fba4f18b321d8ac693db0bb.png
[1020928-20190724164435977-420745969.png]: /images/20211104/169e03e147354133b519722285e5ff34.png
[1020928-20190724164507422-1621484615.png]: /images/20211104/fed1febde4434f14b1f87466fbea96ee.png
[1020928-20190724165428216-1234011502.png]: /images/20211104/7dc01791af3943a1a19b4bc9c7c58ea5.png
[1020928-20190724165459876-615645353.png]: /images/20211104/51378c24722647ceadb64442868694c5.png
[1020928-20190724165526456-1636096364.png]: /images/20211104/afdf4dc6327149e19ba6311482218f0f.png
[1020928-20190724165559322-1269735186.png]: /images/20211104/76259f05c5c54f71907881a655dd6a6b.png
[1020928-20190724165630956-415737578.png]: /images/20211104/9b7c3ecb422940bdaf08ac3e918c1e63.png
[1020928-20190724165708728-992419485.png]: /images/20211104/dde3593ca7184b0498655775013881f4.png
[1020928-20190724165741307-1775117322.png]: /images/20211104/7f6c30ec961c4ba4bc3d0a9cf673b26b.png
[1020928-20190724165815030-1279158485.png]: /images/20211104/c9b72cc371eb45db8df6af644307f84a.png
[1020928-20190724165836814-2011194405.png]: /images/20211104/3c8888397fad46b6951c6d98106eaffa.png
[1020928-20190724165908551-456441605.png]: /images/20211104/8c4f18b081834adba6c810b36d10a0ad.png
[1020928-20190724165944518-211266543.png]: /images/20211104/d3d23c75f9c74f53b115352152ec9a9d.png
[1020928-20190724170017305-1243557085.png]: /images/20211104/435d272bd25a4d5c8554edf6514b2be8.png
[1020928-20190724170050403-1134644492.png]: /images/20211104/264dfbcd614d4bbc9c2b181e6e8017ad.png
[1020928-20190724170126315-851146659.png]: /images/20211104/81d3b7c72f3d4d6baf52fdcda8c45402.png
[1020928-20190724170203922-1539483470.png]: /images/20211104/a7dd1654fa814c369908d5c132cf4331.png
[1020928-20190724170234295-572526910.png]: /images/20211104/6ad88ddcea2c4417b03fad95abc5b874.png
[1020928-20190724170302901-228557936.png]: /images/20211104/99353962c0b9422c8566e91cdcae163c.png
[1020928-20190724170329583-1697755483.png]: /images/20211104/e63691a7e16d4169a9b2ff32a259c3cd.png
[1020928-20190724170357115-1453359752.png]: /images/20211104/047b00dbed564fcf8535c500bc23d5a5.png
[1020928-20190724170422109-40253302.png]: /images/20211104/d68a82f139cb47ba8987c70e31ce816f.png
[1020928-20190724170459357-152223509.png]: /images/20211104/d9185448359140efb399f0fd6812979a.png
[1020928-20190724170515170-1221221095.png]: /images/20211104/d94408218ea84d649d3f3dd334e3c57c.png
[1020928-20190724170540942-1249556108.png]: /images/20211104/cf88fecd8b974535982a4b44e1602664.png
[1020928-20190724170626935-67862072.png]: /images/20211104/433c8824be05445faeb42ed2d048d40a.png
[1020928-20190724170714930-509594391.png]: /images/20211104/28c88e9fd9c64b28863bd5c0374bc9f3.png
[1020928-20190724170746738-1878210397.png]: /images/20211104/1f8d4f45a729442e9c10360b8edcef74.png
[1020928-20190724170835283-1891431769.png]: /images/20211104/5aca5c4cd79941e7b7d3d61ca6edd22d.png
[1020928-20190724170917711-1252248179.png]: /images/20211104/9f2c5047622c42ad90e56649452e890e.png