In [1]:

    

import pandas as pd

import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline


    

In [2]:

    

df = pd.read_csv("/data/iris.csv")
df.head()


    

    
Out[2]:







  

    

      

      
Id
      
SepalLengthCm
      
SepalWidthCm
      
PetalLengthCm
      
PetalWidthCm
      
Species
    
  
  

    

      
0
      
1
      
5.1
      
3.5
      
1.4
      
0.2
      
Iris-setosa
    
    

      
1
      
2
      
4.9
      
3.0
      
1.4
      
0.2
      
Iris-setosa
    
    

      
2
      
3
      
4.7
      
3.2
      
1.3
      
0.2
      
Iris-setosa
    
    

      
3
      
4
      
4.6
      
3.1
      
1.5
      
0.2
      
Iris-setosa
    
    

      
4
      
5
      
5.0
      
3.6
      
1.4
      
0.2
      
Iris-setosa
    
  

In [3]:

    

features = ["SepalLengthCm", "PetalLengthCm"]


    

In [4]:

    

df.Species.value_counts()


    

    
Out[4]:





Iris-versicolor    50
Iris-virginica     50
Iris-setosa        50
Name: Species, dtype: int64

In [5]:

    

fig, ax = plt.subplots()
colors = ["red", "green", "blue"]

for i, v in enumerate(df.Species.unique()):
    df[df.Species == v].plot.scatter(features[0], features[1], label = v
                                , ax = ax, color = colors[i])


    

In [6]:

    

from sklearn import *
from mlxtend.plotting import plot_decision_regions


    

In [7]:

    

y = np.where(df.Species == "Iris-setosa", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=2
    #                                , include_bias=False)),
    ("scaler", preprocessing.StandardScaler()),
    ("est", linear_model.LogisticRegression(random_state = 1, solver="lbfgs"))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 1.0
precision: 1.0
recall: 1.0
f1_score: 1.0






    
Out[7]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a1eb177f0>






    

In [8]:

    

y = np.where(df.Species == "Iris-virginica", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=2
    #                                , include_bias=False)),
    ("scaler", preprocessing.StandardScaler()),
    ("est", linear_model.LogisticRegression(random_state = 1, solver="lbfgs"))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9777777777777777
precision: 0.9285714285714286
recall: 1.0
f1_score: 0.962962962962963






    
Out[8]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a1eb175c0>






    

In [9]:

    

y = np.where(df.Species == "Iris-versicolor", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=2
    #                                , include_bias=False)),
    ("scaler", preprocessing.StandardScaler()),
    ("est", linear_model.LogisticRegression(random_state = 1, solver="lbfgs"))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.6
precision: 0.0
recall: 0.0
f1_score: 0.0






    




/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py:1143: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples.
  'precision', 'predicted', average, warn_for)
/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py:1143: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 due to no predicted samples.
  'precision', 'predicted', average, warn_for)






    
Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x10aa0dd68>






    

In [10]:

    

y = np.where(df.Species == "Iris-versicolor", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    ("poly", preprocessing.PolynomialFeatures(degree=4
                                    , include_bias=False)),
    ("scaler", preprocessing.StandardScaler()),
    ("est", linear_model.LogisticRegression(random_state = 1, solver="lbfgs"))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9333333333333333
precision: 0.9411764705882353
recall: 0.8888888888888888
f1_score: 0.9142857142857143






    
Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x10aa0d550>






    

In [11]:

    

y = np.where(df.Species == "Iris-versicolor", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=4
    #                                , include_bias=False)),
    #("scaler", preprocessing.StandardScaler()),
    ("est", tree.DecisionTreeClassifier(random_state = 1, max_depth=3))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9777777777777777
precision: 1.0
recall: 0.9444444444444444
f1_score: 0.9714285714285714






    
Out[11]:





<matplotlib.axes._subplots.AxesSubplot at 0x10aa75588>






    

In [16]:

    

y = np.where(df.Species == "Iris-versicolor", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=4
    #                                , include_bias=False)),
    #("scaler", preprocessing.StandardScaler()),
    ("est", ensemble.RandomForestClassifier(random_state = 1, max_depth=3, n_estimators=20))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9777777777777777
precision: 1.0
recall: 0.9444444444444444
f1_score: 0.9714285714285714






    
Out[16]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a20006470>






    

In [13]:

    

y = np.where(df.Species == "Iris-versicolor", 1, 0)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=4
    #                                , include_bias=False)),
    #("scaler", preprocessing.StandardScaler()),
    ("est", neighbors.KNeighborsClassifier(n_neighbors=5))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
print("precision:", metrics.precision_score(y_test, y_test_pred))
print("recall:", metrics.recall_score(y_test, y_test_pred))
print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9555555555555556
precision: 1.0
recall: 0.8888888888888888
f1_score: 0.9411764705882353






    
Out[13]:





<matplotlib.axes._subplots.AxesSubplot at 0x10b5cc7f0>






    

In [14]:

    

y = preprocessing.LabelEncoder().fit_transform(df.Species)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    #("poly", preprocessing.PolynomialFeatures(degree=4
    #                                , include_bias=False)),
    #("scaler", preprocessing.StandardScaler()),
    ("est", neighbors.KNeighborsClassifier(n_neighbors=5))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
#print("precision:", metrics.precision_score(y_test, y_test_pred))
##print("recall:", metrics.recall_score(y_test, y_test_pred))
#print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9555555555555556






    
Out[14]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a235989e8>






    

In [15]:

    

y = preprocessing.LabelEncoder().fit_transform(df.Species)
X = df[features].values
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y
                    , test_size = 0.3, random_state = 1)

pipe = pipeline.Pipeline([
    ("poly", preprocessing.PolynomialFeatures(degree=3
                                    , include_bias=False)),
    ("scaler", preprocessing.StandardScaler()),
    ("est", linear_model.LogisticRegression(random_state=1
                            , multi_class="ovr"
                            , solver = "liblinear"))
])

pipe.fit(X_train, y_train)

y_train_pred = pipe.predict(X_train)
y_test_pred = pipe.predict(X_test)
y_test_prob = pipe.predict_proba(X_test)[:,1]

print("accuracy:", metrics.accuracy_score(y_test, y_test_pred))
#print("precision:", metrics.precision_score(y_test, y_test_pred))
##print("recall:", metrics.recall_score(y_test, y_test_pred))
#print("f1_score:", metrics.f1_score(y_test, y_test_pred))

plt.figure(figsize = (8,8))
plot_decision_regions(X, y, pipe, X_highlight=X_test)


    

    




accuracy: 0.9333333333333333






    
Out[15]:





<matplotlib.axes._subplots.AxesSubplot at 0x1a1ffbbf98>






    

In [ ]: