interactive_ml/interactive_ml.py at main · work-with-arslan/interactive_ml · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
import streamlit as st
from sklearn import datasets
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt

st.set_page_config("Interactive ML")
st.title("Explore different classifier")

st.sidebar.markdown(""" **Developed by** [M.Arslan Akram](https://www.linkedin.com/in/arslanakram1/)
    """)
st.sidebar.markdown(""" **Source Code ** [Github](https://github.com/MuhammadArslanAkram/interactive_ml)
    """)

dataset_name=st.sidebar.selectbox("Select DataSet",("Iris","Breast Cancer","Wine"))
classifier_name=st.sidebar.selectbox("Select Classifier",("KNN","SVM","Random Forest"))

def get_dataset(dataset_name):

    if dataset_name=="Iris":
        data = datasets.load_iris()

    elif dataset_name=="Breast Cancer":
        data = datasets.load_breast_cancer()

    else:
        data = datasets.load_wine()

    X=data.data
    y=data.target
    return X,y

X,y=get_dataset(dataset_name)
st.markdown(f""" Selected DataSet is :
**{dataset_name}**
""")
st.write("Shape of dataset :",X.shape)

st.markdown(f""" Selected Classifier is :
** {classifier_name} **
""")

def add_parameter_ui(clf_name):
    params=dict()

    if clf_name=="KNN":
        K = st.sidebar.slider("K",1,15,step=1)
        params["K"]=K

    elif clf_name=="SVM":
        C = st.sidebar.slider("C",0.01,10.0)
        params["C"]=C

    else:
        max_depth = st.sidebar.slider("max depth",2,15)
        n_estimators = st.sidebar.slider("n_estimator",1,100)
        params["max_depth"] = max_depth
        params["n_estimators"] = n_estimators

    return params

params = add_parameter_ui(classifier_name)

def get_classifier(clf_name,params):

    if clf_name=="KNN":
        clf = KNeighborsClassifier(n_neighbors=params["K"])

    elif clf_name=="SVM":
        clf = SVC(C=params["C"])

    else:
        clf = RandomForestClassifier(n_estimators=params["n_estimators"],
                                     max_depth=params["max_depth"],random_state=1234)

    return clf

clf = get_classifier(classifier_name,params)

### Classification
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)
clf.fit(X_train,y_train)

y_pred=clf.predict(X_test)

acc=accuracy_score(y_test,y_pred)
st.markdown(f"""Accuracy : ** {acc} ** """)

## Ploting
pca = PCA(2)
X_projeted = pca.fit_transform(X)

X1=X_projeted[:,0]
X2=X_projeted[:,1]

fig,ax=plt.subplots()

plt.scatter(X1,X2,c=y,alpha=0.8,cmap="viridis")
plt.xlabel("Principal Component 1")
plt.ylabel("Principal Component 2")
plt.colorbar()
st.pyplot(fig)