-
Notifications
You must be signed in to change notification settings - Fork 0
/
Iris.py
157 lines (119 loc) · 5.06 KB
/
Iris.py
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
flowers_data = pd.read_csv(r'C:\Users\imane\OneDrive\Desktop\Iris\Iris.csv', sep =",", encoding = "utf-8")
flowers_data.info()
flowers_data = flowers_data.drop("Id", axis = 1)
print(flowers_data)
flowers_data.hist(bins=70, figsize=(20, 15))
plt.show()
sns.heatmap(flowers_data.corr(),annot = True)
plt.show()
sns.lmplot( x="SepalLengthCm", y="SepalWidthCm", data= flowers_data, fit_reg=False, hue='Species', legend=True)
plt.show()
sns.lmplot( x="PetalLengthCm", y="PetalWidthCm", data= flowers_data, fit_reg=False, hue='Species', legend=True)
plt.show()
sns.violinplot(y = flowers_data["SepalLengthCm"], x = flowers_data["Species"])
plt.show()
sns.violinplot(y = flowers_data["SepalWidthCm"], x = flowers_data["Species"])
plt.show()
sns.violinplot(y = flowers_data["PetalLengthCm"], x = flowers_data["Species"])
plt.show()
sns.violinplot(y = flowers_data["PetalWidthCm"], x = flowers_data["Species"])
plt.show()
from sklearn.model_selection import train_test_split
train_set, test_set = train_test_split(flowers_data, test_size = 0.2,random_state = 42)
train_set_labels = train_set["Species"].copy()
train_set = train_set.drop("Species", axis = 1)
test_set_labels = test_set["Species"].copy()
test_set = test_set.drop("Species", axis = 1)
from sklearn.preprocessing import MinMaxScaler as Scaler
scaler = Scaler()
scaler.fit(train_set)
scaled_train_set = scaler.transform(train_set)
scaled_test_set = scaler.transform(test_set)
scaled_df = pd.DataFrame(data = scaled_train_set)
print(scaled_df)
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
import xgboost as xgb
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn import model_selection
from sklearn.multiclass import OneVsRestClassifier
models = []
models.append(("LogReg", LogisticRegression()))
models.append(("RanFor", RandomForestClassifier()))
models.append(("DecTree", DecisionTreeClassifier()))
models.append(("KNN",KNeighborsClassifier()))
models.append(("SVC",SVC()))
models.append(("XGB",OneVsRestClassifier(xgb.XGBClassifier(use_label_encoder=False,eval_metric='mlogloss'))))
seed = 7
results = []
names = []
X = scaled_train_set
Y = train_set_labels
for name, model in models:
kfolds = model_selection.KFold(n_splits=10)
cv_results = model_selection.cross_val_score(model, X, Y, cv=kfolds, scoring="accuracy")
results.append(cv_results)
names.append(name)
outcome = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
print(outcome)
figure = plt.figure()
figure.suptitle("Algorithms performance")
ax = figure.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()
petals_data = flowers_data[["PetalLengthCm","PetalWidthCm","Species"]]
train_set_petals, test_set_petals = train_test_split(petals_data, test_size = 0.2,random_state = 42)
train_set_labels_petals = train_set_petals["Species"].copy()
train_set_petals = train_set_petals.drop("Species", axis = 1)
test_set_labels_petals = test_set_petals["Species"].copy()
test_set_petals = test_set_petals.drop("Species", axis = 1)
scaler_petals = Scaler()
scaler_petals.fit(train_set_petals)
scaled_train_set_petals = scaler_petals.transform(train_set_petals)
scaled_test_set_petals = scaler_petals.transform(test_set_petals)
scaled_df_petals = pd.DataFrame(data = scaled_train_set_petals)
models_petals = []
models_petals.append(("LogReg", LogisticRegression()))
models_petals.append(("RanFor", RandomForestClassifier()))
models_petals.append(("DecTree", DecisionTreeClassifier()))
models_petals.append(("KNN",KNeighborsClassifier()))
models_petals.append(("SVC",SVC()))
models_petals.append(("XGB",OneVsRestClassifier(xgb.XGBClassifier(use_label_encoder=False,eval_metric='mlogloss'))))
seed_petals = 7
results_petals = []
names_petals = []
X_petals = scaled_train_set_petals
Y_petals = train_set_labels_petals
for name, model in models_petals:
kfolds = model_selection.KFold(n_splits=10)
cv_results_petals = model_selection.cross_val_score(model, X_petals, Y_petals, cv=kfolds, scoring="accuracy")
results_petals.append(cv_results_petals)
names_petals.append(name)
outcome_petals = "%s: %f (%f)" % (name, cv_results_petals.mean(), cv_results_petals.std())
print(outcome_petals)
figure_petals = plt.figure()
figure.suptitle("Algorithms performance on Petals data")
ax_petals = figure_petals.add_subplot(111)
plt.boxplot(results_petals)
ax_petals.set_xticklabels(names_petals)
plt.show()
from sklearn.model_selection import GridSearchCV
model_params = {
'n_estimators': [50, 150, 250],
'max_features': ['sqrt', 0.25, 0.5, 0.75, 1.0],
'min_samples_split': [2, 4, 6]
}
rf_model = RandomForestClassifier(random_state=42)
clf = GridSearchCV(rf_model, model_params, cv=5)
model = clf.fit(X_petals,Y_petals)
print(model.best_params_)
predictions = model.predict(scaled_test_set_petals)
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(test_set_labels_petals, predictions)
print("Accuracy: ", accuracy)