commit-live-students · prodigy803 · Nov 11, 2018 · Nov 13, 2018 · Nov 22, 2018 · Nov 22, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_plot_corr/__pycache__/__init__.cpython-36.pyc b/q01_plot_corr/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_plot_corr/__pycache__/build.cpython-36.pyc b/q01_plot_corr/__pycache__/build.cpython-36.pyc
diff --git a/q01_plot_corr/build.py b/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 +11,14 @@
 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)
+    plt.show()
     return ax
+
+
+
+
+
diff --git a/q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc b/q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_plot_corr/tests/__pycache__/test_q01_plot_corr.cpython-36.pyc b/q01_plot_corr/tests/__pycache__/test_q01_plot_corr.cpython-36.pyc
diff --git a/q02_best_k_features/__pycache__/__init__.cpython-36.pyc b/q02_best_k_features/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_best_k_features/__pycache__/build.cpython-36.pyc b/q02_best_k_features/__pycache__/build.cpython-36.pyc
diff --git a/q02_best_k_features/build.py b/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 +11,19 @@
 
 
 # Write your solution here:
+def percentile_k_features(df,k=20):
+    X = df.iloc[:,:-1]
+    y= df.iloc[:,-1]
+    selection = SelectPercentile(f_regression, percentile=k)
+    x_features = selection.fit_transform(X, y)
+    columns = np.asarray(X.columns.values)
+    support = np.asarray(selection.get_support())
+    columns_with_support = columns[support]
+    return list(columns_with_support)
+
+
+
+
+
+
 
diff --git a/q02_best_k_features/tests/__pycache__/__init__.cpython-36.pyc b/q02_best_k_features/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_best_k_features/tests/__pycache__/test_q02_percentile_k_features.cpython-36.pyc b/q02_best_k_features/tests/__pycache__/test_q02_percentile_k_features.cpython-36.pyc
diff --git a/q03_rf_rfe/__pycache__/__init__.cpython-36.pyc b/q03_rf_rfe/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_rf_rfe/__pycache__/build.cpython-36.pyc b/q03_rf_rfe/__pycache__/build.cpython-36.pyc
diff --git a/q03_rf_rfe/build.py b/q03_rf_rfe/build.py
@@ -1,5 +1,7 @@
+# %load q03_rf_rfe/build.py
 # Default imports
 import pandas as pd
+import numpy as np
 
 data = pd.read_csv('data/house_prices_multivariate.csv')
 
@@ -8,4 +10,23 @@
 
 
 # Your solution code here
+def rf_rfe(df):
+    rfe = RandomForestClassifier()
+    X,y = df.iloc[:,:-1],df.iloc[:,-1]
+
+    selector = RFE(rfe, step=1)
+    selector = selector.fit(X, y)
+
+    arr_columns = np.array(df.columns)
+    arr = np.select([selector.get_support()],[arr_columns[:-1]] )
+    return arr[arr!=0].tolist()
+
+
+
+
+
+
+
+
+
 
diff --git a/q03_rf_rfe/tests/__pycache__/__init__.cpython-36.pyc b/q03_rf_rfe/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_rf_rfe/tests/__pycache__/test_q03_rf_rfe.cpython-36.pyc b/q03_rf_rfe/tests/__pycache__/test_q03_rf_rfe.cpython-36.pyc
diff --git a/q04_select_from_model/__pycache__/__init__.cpython-36.pyc b/q04_select_from_model/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_select_from_model/__pycache__/build.cpython-36.pyc b/q04_select_from_model/__pycache__/build.cpython-36.pyc
diff --git a/q04_select_from_model/build.py b/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 +9,17 @@
 
 
 # Your solution code here
+def select_from_model(df):
+
+    X = df.iloc[:,:-1]
+    y = df.iloc[:,-1]
+    rf = RandomForestClassifier()
+    slm = SelectFromModel(rf)
+    slm.fit(X,y)
+    slm.get_support()
+    columns = np.array(df.columns[:-1])
+    return columns[slm.get_support()[:]].tolist()
+
+
+
+
diff --git a/q04_select_from_model/tests/__pycache__/__init__.cpython-36.pyc b/q04_select_from_model/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_select_from_model/tests/__pycache__/test_q04_select_from_model.cpython-36.pyc b/q04_select_from_model/tests/__pycache__/test_q04_select_from_model.cpython-36.pyc