Code

# ## Name: Zixuan Li
# ## Date: 10/20/2022
# ## Class Section: 4
# ## Lab Section: 5

Code

import pandas as pd
import seaborn as sns 
import matplotlib.pyplot as plt
from sklearn import tree
from IPython.display import Image
import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score

Code

# LOAD THE DATAFRAME
from sklearn.datasets import load_breast_cancer
(x,y) = load_breast_cancer(return_X_y=True,as_frame=True)
df=pd.concat([x,y],axis=1)

# LOOK AT FIRST ROW
print(df.iloc[0])

mean radius                  17.990000
mean texture                 10.380000
mean perimeter              122.800000
mean area                  1001.000000
mean smoothness               0.118400
mean compactness              0.277600
mean concavity                0.300100
mean concave points           0.147100
mean symmetry                 0.241900
mean fractal dimension        0.078710
radius error                  1.095000
texture error                 0.905300
perimeter error               8.589000
area error                  153.400000
smoothness error              0.006399
compactness error             0.049040
concavity error               0.053730
concave points error          0.015870
symmetry error                0.030030
fractal dimension error       0.006193
worst radius                 25.380000
worst texture                17.330000
worst perimeter             184.600000
worst area                 2019.000000
worst smoothness              0.162200
worst compactness             0.665600
worst concavity               0.711900
worst concave points          0.265400
worst symmetry                0.460100
worst fractal dimension       0.118900
target                        0.000000
Name: 0, dtype: float64

Code

print(df.keys())

Index(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
       'mean smoothness', 'mean compactness', 'mean concavity',
       'mean concave points', 'mean symmetry', 'mean fractal dimension',
       'radius error', 'texture error', 'perimeter error', 'area error',
       'smoothness error', 'compactness error', 'concavity error',
       'concave points error', 'symmetry error', 'fractal dimension error',
       'worst radius', 'worst texture', 'worst perimeter', 'worst area',
       'worst smoothness', 'worst compactness', 'worst concavity',
       'worst concave points', 'worst symmetry', 'worst fractal dimension',
       'target'],
      dtype='object')

Code

df2 = pd.DataFrame()
df2['columns']= df.columns
df2['dtypes']=list(df.dtypes)
df2['min']=list(df.min())
df2['mean']=list(df.mean())
df2['max']=list(df.max())
print(df2.to_markdown(index=False))

| columns                 | dtypes   |         min |         mean |        max |
|:------------------------|:---------|------------:|-------------:|-----------:|
| mean radius             | float64  |   6.981     |  14.1273     |   28.11    |
| mean texture            | float64  |   9.71      |  19.2896     |   39.28    |
| mean perimeter          | float64  |  43.79      |  91.969      |  188.5     |
| mean area               | float64  | 143.5       | 654.889      | 2501       |
| mean smoothness         | float64  |   0.05263   |   0.0963603  |    0.1634  |
| mean compactness        | float64  |   0.01938   |   0.104341   |    0.3454  |
| mean concavity          | float64  |   0         |   0.0887993  |    0.4268  |
| mean concave points     | float64  |   0         |   0.0489191  |    0.2012  |
| mean symmetry           | float64  |   0.106     |   0.181162   |    0.304   |
| mean fractal dimension  | float64  |   0.04996   |   0.0627976  |    0.09744 |
| radius error            | float64  |   0.1115    |   0.405172   |    2.873   |
| texture error           | float64  |   0.3602    |   1.21685    |    4.885   |
| perimeter error         | float64  |   0.757     |   2.86606    |   21.98    |
| area error              | float64  |   6.802     |  40.3371     |  542.2     |
| smoothness error        | float64  |   0.001713  |   0.00704098 |    0.03113 |
| compactness error       | float64  |   0.002252  |   0.0254781  |    0.1354  |
| concavity error         | float64  |   0         |   0.0318937  |    0.396   |
| concave points error    | float64  |   0         |   0.0117961  |    0.05279 |
| symmetry error          | float64  |   0.007882  |   0.0205423  |    0.07895 |
| fractal dimension error | float64  |   0.0008948 |   0.0037949  |    0.02984 |
| worst radius            | float64  |   7.93      |  16.2692     |   36.04    |
| worst texture           | float64  |  12.02      |  25.6772     |   49.54    |
| worst perimeter         | float64  |  50.41      | 107.261      |  251.2     |
| worst area              | float64  | 185.2       | 880.583      | 4254       |
| worst smoothness        | float64  |   0.07117   |   0.132369   |    0.2226  |
| worst compactness       | float64  |   0.02729   |   0.254265   |    1.058   |
| worst concavity         | float64  |   0         |   0.272188   |    1.252   |
| worst concave points    | float64  |   0         |   0.114606   |    0.291   |
| worst symmetry          | float64  |   0.1565    |   0.290076   |    0.6638  |
| worst fractal dimension | float64  |   0.05504   |   0.0839458  |    0.2075  |
| target                  | int64    |   0         |   0.627417   |    1       |

Code

sum0 = sum(df['target']==0)
sum1 = sum(df['target']==1)
sum0_1 = sum0+sum1
print('Number of points with target=0: ',sum0,sum0/(sum0_1))
print('Number of points with target=1: ',sum1,sum1/(sum0_1))

Number of points with target=0:  212 0.37258347978910367
Number of points with target=1:  357 0.6274165202108963

Code

corr = df.corr();  #print(corr)                 #COMPUTE CORRELATION OF FEATER MATRIX
print(corr.shape)
sns.set_theme(style="white")
f, ax = plt.subplots(figsize=(20, 20))  # Set up the matplotlib figure
cmap = sns.diverging_palette(230, 20, as_cmap=True)     # Generate a custom diverging colormap
# Draw the heatmap with the mask and correct aspect ratio
sns.heatmap(corr,  cmap=cmap, vmin=-1, vmax=1, center=0,
        square=True, linewidths=.5, cbar_kws={"shrink": .5})
plt.show();

(31, 31)

Code

# # RUN THE FOLLOWING CODE TO GENERATE A SEABORN PAIRPLOT 
tmp=pd.concat([df.sample(n=10,axis=1),y],axis=1)
print(tmp.shape)
sns.pairplot(tmp,hue="target", diag_kind='kde')
plt.show()

(569, 11)

Code

Y = df['target']
X = df.drop(columns=['target'])

Code

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=0)

Code

print("x_train.shape : ",x_train.shape)
print("y_train.shape : ",x_train.shape)
print("x_test.shape : ",x_test.shape)
print("y_test.shape : ",y_test.shape)

x_train.shape :  (455, 30)
y_train.shape :  (455, 30)
x_test.shape :  (114, 30)
y_test.shape :  (114,)

Code

from sklearn import tree
model = tree.DecisionTreeClassifier()
model = model.fit(x_train, y_train)

Code

from sklearn.datasets import make_classification
from sklearn.svm import SVC
clf = SVC(random_state=0)
clf.fit(x_train, y_train)
yp_train = model.predict(x_train)
yp_test = model.predict(x_test)

Code

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
plt.rcParams['figure.figsize']=10,10
def confusion_plot(y_data,y_pred):
    dt = confusion_matrix(y_data, y_pred)
    disp = ConfusionMatrixDisplay(confusion_matrix=dt)
    disp.plot()
    return plt.show()
confusion_plot(y_test,yp_test)
a = accuracy_score(y_test, yp_test)
nr = recall_score(y_test, yp_test, labels=0)
np= precision_score(y_test, yp_test, labels=0)
pr= recall_score(y_test, yp_test, labels=1)
pp= precision_score(y_test, yp_test, labels=1)
dt = confusion_matrix(y_test, yp_test)
print("ACCURACY: ",a, 
"\nNEGATIVE RECALL (Y=0): ", nr,
"\nNEGATIVE PRECISION (Y=0): " , np,
"\nPOSITIVE RECALL (Y=1): ", pr,
"\nPOSITIVE PRECISION (Y=1): ", pp,
"\n",dt)

ACCURACY:  0.9035087719298246 
NEGATIVE RECALL (Y=0):  0.8805970149253731 
NEGATIVE PRECISION (Y=0):  0.9516129032258065 
POSITIVE RECALL (Y=1):  0.8805970149253731 
POSITIVE PRECISION (Y=1):  0.9516129032258065 
 [[44  3]
 [ 8 59]]

Code

print("------TRAINING------")
confusion_plot(y_train,yp_train)
print("------TEST------")
confusion_plot(y_test,yp_test)

------TRAINING------

------TEST------

Code

from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier 
def plot_tree(model,X,Y):
    feature_names = X.columns
    target_names = str(Y.unique().tolist())
    model = tree.DecisionTreeClassifier()
    clf = model.fit(X, Y)
    fig = plt.figure(figsize=(25,20))
    tree.plot_tree(clf, 
                   feature_names=feature_names,  
                   class_names=target_names,
                   filled=True)
    return plt.show()

Code

test_results=[]
train_results=[]

for num_layer in range(1,20):
    model = tree.DecisionTreeClassifier(max_depth=num_layer)
    clf = model.fit(x_train, y_train)

    yp_train=clf.predict(x_train)
    yp_test=clf.predict(x_test)

    # print(y_pred.shape)
    test_results.append([num_layer,accuracy_score(y_test, yp_test),recall_score(y_test, yp_test,pos_label=0),recall_score(y_test, yp_test,pos_label=1)])
    train_results.append([num_layer,accuracy_score(y_train,yp_train),recall_score(y_train, yp_train,pos_label=0),recall_score(y_train, yp_train,pos_label=1)])

Code

test_results = pd.DataFrame(test_results)
train_results = pd.DataFrame(train_results)

plt.rcParams[‘figure.figsize’]=8,7 plt.plot(train_results[1], label=‘train’,marker = ‘o’) plt.plot(test_results[1], label=‘test’,marker = ‘o’) plt.xlabel(‘Number of layers in decision trees(max_depth)’,fontsize=18) plt.ylabel(‘Accuracy: training and test’,fontsize=18) plt.legend(fontsize=15) plt.show()

plt.plot(train_results[2], label=‘train’,marker = ‘o’) plt.plot(test_results[2], label=‘test’,marker = ‘o’) plt.xlabel(‘Number of layers in decision trees(max_depth)’,fontsize=18) plt.ylabel(‘Recall(y=0): training and test’,fontsize=18) plt.legend(fontsize=15) plt.show()

plt.plot(train_results[3], label=‘train’,marker = ‘o’) plt.plot(test_results[3], label=‘test’,marker = ‘o’) plt.xlabel(‘Number of layers in decision trees(max_depth)’,fontsize=18) plt.ylabel(‘Recall(y=1): training and test’,fontsize=18) plt.legend(fontsize=15) plt.show()

Code

from sklearn import tree
model = tree.DecisionTreeClassifier(max_depth=max(train_results[0]))
model = model.fit(x_train, y_train)

yp_train=model.predict(x_train)
yp_test=model.predict(x_test)

Code

print("------TRAINING------")
confusion_plot(y_train,yp_train)
print("------TEST------")
confusion_plot(y_test,yp_test)

plot_tree(model,X,Y)

------TRAINING------

------TEST------