Commit Live PR

q01_plot_corr/build.py

@@ -1,16 +1,21 @@
+# %load q01_plot_corr/build.py
 # Default imports
 import pandas as pd
 from matplotlib.pyplot import yticks, xticks, subplots, set_cmap
-plt.switch_backend('agg')
+# plt.switch_backend('agg')
+# % matplotlib inline
 data = pd.read_csv('data/house_prices_multivariate.csv')
 
 
 # Write your solution here:
 def plot_corr(data, size=11):
     corr = data.corr()
     fig, ax = subplots(figsize=(size, size))
-    set_cmap("YlOrRd")
+    set_cmap('YlOrRd')
     ax.matshow(corr)
     xticks(range(len(corr.columns)), corr.columns, rotation=90)
     yticks(range(len(corr.columns)), corr.columns)
     return ax
+# plot_corr(data,size=11)
+
+

q02_best_k_features/build.py

@@ -1,12 +1,26 @@
+# %load q02_best_k_features/build.py
 # Default imports
 
 import pandas as pd
-
+import numpy as np
 data = pd.read_csv('data/house_prices_multivariate.csv')
 
 from sklearn.feature_selection import SelectPercentile
 from sklearn.feature_selection import f_regression
 
 
 # Write your solution here:
+def percentile_k_features(df,k = 20):
+    X = df.drop(['SalePrice'], axis = 1)
+    y = df['SalePrice']
+
+    selector = SelectPercentile(f_regression, k)
+    X_new = selector.fit_transform(X, y)
+
+    featurelist = list(X.columns.values[np.argsort(selector.scores_)[-1:-X_new.shape[1]-1:-1]])
+
+    return featurelist
+
+# percentile_k_features(data,20)
+
 

q03_rf_rfe/build.py

@@ -1,3 +1,4 @@
+# %load q03_rf_rfe/build.py
 # Default imports
 import pandas as pd
 
@@ -9,3 +10,17 @@
 
 # Your solution code here
 
+def rf_rfe(df):
+    X = df.drop('SalePrice',axis=1)
+    y = df['SalePrice']
+
+    model = RandomForestClassifier()
+    rfe = RFE(model,n_features_to_select=len(X.columns)/2)
+    rfe = rfe.fit(X,y)
+
+    return list(X.columns[rfe.support_])
+
+# rf_rfe(data)
+
+
+

q04_select_from_model/build.py

@@ -1,3 +1,4 @@
+# %load q04_select_from_model/build.py
 # Default imports
 from sklearn.feature_selection import SelectFromModel
 from sklearn.ensemble import RandomForestClassifier
@@ -8,3 +9,19 @@
 
 
 # Your solution code here
+def select_from_model(data):
+    X = data.drop('SalePrice',axis=1)
+    y = data['SalePrice']
+
+    model = RandomForestClassifier()
+
+    sfm = SelectFromModel(model)
+    sfm.fit_transform(X,y)
+
+    feature_name = list(X.columns[sfm.get_support()])
+
+    return feature_name
+
+# select_from_model(data)
+
+

q05_forward_selected/build.py

@@ -1,5 +1,7 @@
+# %load q05_forward_selected/build.py
 # Default imports
 import pandas as pd
+import numpy as np
 from sklearn.linear_model import LinearRegression
 
 data = pd.read_csv('data/house_prices_multivariate.csv')
@@ -8,3 +10,34 @@
 
 
 # Your solution code here
+
+def forward_selected(df, model):
+    X = df.drop('SalePrice', axis=1)
+    y = df['SalePrice']
+    X_list = list(X.columns)
+    best_X = []
+    best_r2 = []
+
+    while len(X_list) > 0:
+        r2_X = []
+
+        for Xcol in X_list:
+            best_X.append(Xcol)
+            model.fit(X[best_X], y)
+            r2 = model.score(X[best_X], y)          
+            r2_X.append((r2, Xcol))
+
+            best_X.remove(Xcol)
+
+        r2_X.sort()
+        score, col = r2_X.pop()
+
+        X_list.remove(col)
+
+        best_X.append(col)
+        best_r2.append(score)
+    return best_X, best_r2
+
+# forward_selected(data, model)
+
+