Commit Live PR

q01_plot_corr/build.py

@@ -1,5 +1,7 @@
+# %load q01_plot_corr/build.py
 # Default imports
 import pandas as pd
+import matplotlib.pyplot as plt
 from matplotlib.pyplot import yticks, xticks, subplots, set_cmap
 plt.switch_backend('agg')
 data = pd.read_csv('data/house_prices_multivariate.csv')
@@ -9,8 +11,12 @@
 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)
+
+

q02_best_k_features/build.py

@@ -1,6 +1,8 @@
+# %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')
 
@@ -9,4 +11,15 @@
 
 
 # Write your solution here:
+def percentile_k_features(df, k=20):
+    predictors = df.drop('SalePrice', axis=1)
+    target = df['SalePrice']
+
+    fs = SelectPercentile(f_regression, k)
+    features = fs.fit_transform(predictors, target)
+    features_by_score = [predictors.columns[i] for i in np.argsort(fs.scores_)[::-1]]
+
+    return features_by_score[:7]
+
+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
 
@@ -8,4 +9,17 @@
 
 
 # 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)
+    fit = rfe.fit(X, y)
+
+    features = X.columns[fit.support_]
+    return list(features)
+
+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 +9,15 @@
 
 
 # Your solution code here
+def select_from_model(df):
+    X = df.drop('SalePrice', axis=1)
+    y = df['SalePrice']
+
+    model = RandomForestClassifier()
+    sfm = SelectFromModel(model)
+    sfm.fit_transform(X, y)
+
+    return list(X.columns[sfm.get_support()])
+
+select_from_model(data)
+

q05_forward_selected/build.py

@@ -1,10 +1,46 @@
+# %load q05_forward_selected/build.py
 # Default imports
 import pandas as pd
+import numpy as np
 from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split as tts
+from sklearn.metrics import mean_squared_error, r2_score
 
 data = pd.read_csv('data/house_prices_multivariate.csv')
 
 model = LinearRegression()
 
 
 # Your solution code here
+def forward_selected(df, LinReg):
+    features = df.drop('SalePrice', axis=1)
+    target = df['SalePrice']
+    feature_list = list(features.columns)
+    best_features = []
+    best_scores = []
+
+    while len(feature_list) > 0:
+        scores_with_features = []
+
+        for feature in feature_list:
+            best_features.append(feature)
+
+            LinReg.fit(features[best_features], target)
+            rsquare = LinReg.score(features[best_features], target)          
+            scores_with_features.append((rsquare, feature))
+
+            best_features.remove(feature)
+
+        scores_with_features.sort()
+        best_score, best_candidate = scores_with_features.pop()
+
+        feature_list.remove(best_candidate)
+
+        best_features.append(best_candidate)
+        best_scores.append(best_score)
+
+    return best_features, best_scores 
+
+forward_selected(data, model)
+
+