commit-live-students · dharmil25 · Apr 17, 2018 · Apr 23, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_bagging/__pycache__/__init__.cpython-36.pyc b/q01_bagging/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_bagging/__pycache__/build.cpython-36.pyc b/q01_bagging/__pycache__/build.cpython-36.pyc
diff --git a/q01_bagging/build.py b/q01_bagging/build.py
@@ -1,3 +1,4 @@
+# %load q01_bagging/build.py
 import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeClassifier
@@ -14,5 +15,21 @@
 
 
 # Write your code here
+def bagging(X_train, X_test, y_train, y_test, n_est):
+    lst = []
+    for i in range(1,n_est):
+        bagging_clf2 = BaggingClassifier(DecisionTreeClassifier(), n_estimators=i, max_samples=0.67,
+                                        bootstrap=True, random_state=9, max_features=0.67)
 
-
+        bagging_clf2.fit(X_train, y_train)
+        y_pred_test = bagging_clf2.predict(X_test)
+        y_pred_train = bagging_clf2.predict(X_train)
+        lst.append((i,accuracy_score(y_test, y_pred_test),accuracy_score(y_train,y_pred_train)))
+    df = pd.DataFrame(lst)
+    plt.xlabel('n_estimators')
+    plt.ylabel('accuracy')
+    plt.plot(df.iloc[:,0],df.iloc[:,2],c='b', label='Train set')
+    plt.plot(df.iloc[:,0],df.iloc[:,1],c='g', label='Test set')
+    plt.legend()
+    plt.show()
+    return
diff --git a/q01_bagging/tests/__pycache__/__init__.cpython-36.pyc b/q01_bagging/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_bagging/tests/__pycache__/test_q01_bagging.cpython-36.pyc b/q01_bagging/tests/__pycache__/test_q01_bagging.cpython-36.pyc
diff --git a/q02_stacking_clf/__pycache__/__init__.cpython-36.pyc b/q02_stacking_clf/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_stacking_clf/__pycache__/build.cpython-36.pyc b/q02_stacking_clf/__pycache__/build.cpython-36.pyc
diff --git a/q02_stacking_clf/build.py b/q02_stacking_clf/build.py
@@ -1,4 +1,5 @@
 # Default imports
+from mlxtend.classifier import StackingClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.linear_model import LogisticRegression
@@ -15,4 +16,19 @@
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=9)
 
 # Write your code here
+def stacking_clf(model, X_train, y_train, X_test, y_test):
+    for mod in model:
+        mod.fit(X_train, y_train)
+    X_train1 = X_test1 = pd.DataFrame()
 
+    for mod in model:
+        X_train1 = pd.concat([X_train1,pd.DataFrame(mod.predict_proba(X_train))],axis=1)
+
+    for mod in model:
+        X_test1 = pd.concat([X_test1,pd.DataFrame(mod.predict_proba(X_test))],axis=1)
+
+    meta_clf = LogisticRegression(random_state=9)
+    meta_clf.fit(X_train1,y_train)
+    y_pred = meta_clf.predict(X_test1)
+    accuracy = accuracy_score(y_test, y_pred)
+    return accuracy
diff --git a/q02_stacking_clf/tests/__pycache__/__init__.cpython-36.pyc b/q02_stacking_clf/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_stacking_clf/tests/__pycache__/test_q02_stacking_clf.cpython-36.pyc b/q02_stacking_clf/tests/__pycache__/test_q02_stacking_clf.cpython-36.pyc