commit-live-students · rohanhg91 · May 1, 2018 · May 2, 2018
diff --git a/q01_load_data_and_add_column_names/__pycache__/__init__.cpython-36.pyc b/q01_load_data_and_add_column_names/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data_and_add_column_names/__pycache__/build.cpython-36.pyc b/q01_load_data_and_add_column_names/__pycache__/build.cpython-36.pyc
diff --git a/q01_load_data_and_add_column_names/build.py b/q01_load_data_and_add_column_names/build.py
@@ -1,6 +1,21 @@
+# %load q01_load_data_and_add_column_names/build.py
 import pandas as pd
 
 
 path = 'data/GermanData.csv'
 
-def q01_load_data_and_add_column_names():
+def q01_load_data_and_add_column_names(path):
+    data = pd.read_csv(path,names=['account_status','month','credit_history','purpose','credit_amount','savings_account/bonds','employment','installment_rate','personal_status/sex','guarantors','residence_since','property','age','other_installment_plans','housing','number_of_existing_credits','jobs','liable','telephone','foreign_worker','good/bad'])
+    data['good/bad'] = data['good/bad'].replace(1,0)
+    data['good/bad'] = data['good/bad'].replace(2,1)
+    return data
+
+
+
+
+
+
+
+
+
+
diff --git a/q01_load_data_and_add_column_names/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data_and_add_column_names/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data_and_add_column_names/tests/__pycache__/test.cpython-36.pyc b/q01_load_data_and_add_column_names/tests/__pycache__/test.cpython-36.pyc
diff --git a/q04_correlation_plot/__pycache__/__init__.cpython-36.pyc b/q04_correlation_plot/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_correlation_plot/__pycache__/build.cpython-36.pyc b/q04_correlation_plot/__pycache__/build.cpython-36.pyc
diff --git a/q04_correlation_plot/build.py b/q04_correlation_plot/build.py
@@ -1,9 +1,29 @@
 import matplotlib.pyplot as plt
 import seaborn as sns
-plt.switch_backend('agg')
+from sklearn import preprocessing
+#plt.switch_backend('agg')
 import sys, os
 from greyatomlib.statlog_german_credit_data_project.q03_encode_features.build import q03_encode_features
+from greyatomlib.statlog_german_credit_data_project.q01_load_data_and_add_column_names.build import q01_load_data_and_add_column_names
+
 path = 'data/GermanData.csv'
 
-def q04_correlation_plot():
-
+def q04_correlation_plot(path):
+    a = q01_load_data_and_add_column_names(path)
+    df_corr = a.corr()
+    df_corr.plot(kind='hist')
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/q04_correlation_plot/tests/__pycache__/__init__.cpython-36.pyc b/q04_correlation_plot/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_correlation_plot/tests/__pycache__/test.cpython-36.pyc b/q04_correlation_plot/tests/__pycache__/test.cpython-36.pyc
diff --git a/q05_split/__pycache__/__init__.cpython-36.pyc b/q05_split/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_split/__pycache__/build.cpython-36.pyc b/q05_split/__pycache__/build.cpython-36.pyc
diff --git a/q05_split/build.py b/q05_split/build.py
@@ -1,7 +1,18 @@
+# %load q05_split/build.py
 import sys, os
 from sklearn.model_selection import train_test_split
 from greyatomlib.statlog_german_credit_data_project.q03_encode_features.build import q03_encode_features
 path = 'data/GermanData.csv'
 
-def q05_split():
-
+def q05_split(path,test_size = 0.2,random_state=9):
+    data,data_dict = q03_encode_features(path)
+    Y = data['good/bad']
+    X = data.iloc[:,:-1]
+    X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=test_size, random_state=random_state)
+    return X_train[1:], X_test, y_train[1:], y_test
+
+
+
+
+
+
diff --git a/q05_split/tests/__pycache__/__init__.cpython-36.pyc b/q05_split/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_split/tests/__pycache__/test.cpython-36.pyc b/q05_split/tests/__pycache__/test.cpython-36.pyc