commit-live-students · rianboy18 · Aug 30, 2018 · Sep 4, 2018 · Oct 6, 2018 · Oct 19, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc
diff --git a/q01_load_data/build.py b/q01_load_data/build.py
@@ -1,4 +1,12 @@
+# %load q01_load_data/build.py
 import pandas as pd
-
+path = 'data/student-mat.csv'
 # Write your code below
-
+def load_data(path):
+    df=pd.read_table(path,sep=';')
+    return df
+
+c=load_data(path)
+c
+
+
diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/tests/__pycache__/test.cpython-36.pyc b/q01_load_data/tests/__pycache__/test.cpython-36.pyc
diff --git a/q02_data_split/__pycache__/__init__.cpython-36.pyc b/q02_data_split/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_data_split/__pycache__/build.cpython-36.pyc b/q02_data_split/__pycache__/build.cpython-36.pyc
diff --git a/q02_data_split/build.py b/q02_data_split/build.py
@@ -1,8 +1,24 @@
+# %load q02_data_split/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from sklearn.model_selection import train_test_split
 import pandas as pd
 df = load_data('data/student-mat.csv')
+import numpy as np
 
-# Write your code below
+def split_dataset(df):
+    X=df.iloc[:,:-1]
+    y=df.iloc[:,-1]
+#     for i in range(10):
+#         for j in np.arange(0.0,1.0,0.1):
+#             X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=i,test_size=j)
+#             if (X_train.shape==(316,32)) & (X_test.shape==(79,32)) &  (y_train.shape==(316,)) &  (y_test.shape==(79,)):
+#                 return i,j
+    X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0,test_size=0.20000000000000001)
+    return X_train,X_test,y_train,y_test
 
 
+
+c=split_dataset(df)
+c
+
+
diff --git a/q02_data_split/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_split/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_data_split/tests/__pycache__/test.cpython-36.pyc b/q02_data_split/tests/__pycache__/test.cpython-36.pyc
diff --git a/q03_data_encoding/__pycache__/__init__.cpython-36.pyc b/q03_data_encoding/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_data_encoding/__pycache__/build.cpython-36.pyc b/q03_data_encoding/__pycache__/build.cpython-36.pyc
diff --git a/q03_data_encoding/build.py b/q03_data_encoding/build.py
@@ -1,3 +1,4 @@
+# %load q03_data_encoding/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from sklearn.preprocessing import LabelEncoder
@@ -7,8 +8,16 @@
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
-# Write your code below
+def label_encode(x_train,x_test):
+    X_transform = pd.DataFrame(x_train.apply(LabelEncoder().fit_transform))
+    X_test_transform = pd.DataFrame(x_test.apply(LabelEncoder().fit_transform))
+    return X_transform,X_test_transform
 
 
 
 
+
+c=label_encode(x_train,x_test)
+c
+
+
diff --git a/q03_data_encoding/tests/__pycache__/__init__.cpython-36.pyc b/q03_data_encoding/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_data_encoding/tests/__pycache__/test.cpython-36.pyc b/q03_data_encoding/tests/__pycache__/test.cpython-36.pyc
diff --git a/q03_ohe_encoder/__pycache__/__init__.cpython-36.pyc b/q03_ohe_encoder/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_ohe_encoder/__pycache__/build.cpython-36.pyc b/q03_ohe_encoder/__pycache__/build.cpython-36.pyc
diff --git a/q03_ohe_encoder/build.py b/q03_ohe_encoder/build.py
@@ -1,19 +1,51 @@
+# %load q03_ohe_encoder/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from sklearn.preprocessing import OneHotEncoder
 import pandas as pd
 import numpy as np
-
+from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
 df = load_data('data/student-mat.csv')
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
 category_index = [x for x in range(len(df.columns)) if df[df.columns[x]].dtype == 'object']
 
 
-# Write your code below
 
-
+# def ohe_encode(df,x_test,category_index):
+# ind=[]
+# for i in range(len(list(df))):
+#     ind.append(i)
+
+# a=[]
+# for i,j in zip(list(df),ind):
+#     a.append((j,i))
+
+# main=[]    
+# for i in a:
+#     for j in category_index:
+#         if i[0]==j:
+#             main.append(i[1])
 
+def ohe_encode(X_train,X_test,category_index=category_index):
+    X_train,X_test=label_encode(X_train,X_test)
+#     X_train = pd.get_dummies(X_train)
+#     X_test = pd.get_dummies(X_test)
+    ohe = OneHotEncoder(categorical_features=category_index,sparse=False)
+    ohe.fit(X_train)
+    ohe.fit(X_test)
+    X_train = ohe.transform(X_train)
+    X_test = ohe.transform(X_test)            
 
-
+    return pd.DataFrame(X_train),pd.DataFrame(X_test)  
+#     nc = OneHotEncoder(categorical_features=[len(main)])
+#     model1 = enc.fit_transform(x_train)
+#     model2 = enc.fit_transform(x_test)
+#     return model1
+
+
+c=ohe_encode(x_train,x_test,category_index)
+c
+
+
diff --git a/q03_ohe_encoder/tests/__pycache__/__init__.cpython-36.pyc b/q03_ohe_encoder/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_ohe_encoder/tests/__pycache__/test.cpython-36.pyc b/q03_ohe_encoder/tests/__pycache__/test.cpython-36.pyc
diff --git a/q04_data_visualisation/__pycache__/__init__.cpython-36.pyc b/q04_data_visualisation/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_data_visualisation/__pycache__/build.cpython-36.pyc b/q04_data_visualisation/__pycache__/build.cpython-36.pyc
diff --git a/q04_data_visualisation/build.py b/q04_data_visualisation/build.py
@@ -1,16 +1,25 @@
-# -*- coding: utf-8 -*-
+# %load q04_data_visualisation/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
-
+import matplotlib
+matplotlib.use('Agg')
+import pandas as pd
 import matplotlib.pyplot as plt
 from pandas.plotting import scatter_matrix
 data = load_data('data/student-mat.csv') 
 x_train, x_test, y_train, y_test =  split_dataset(data)
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your code below
-
+def visualise_data(data,figname = 'data/student-mat.csv'):
+    train = pd.concat([x_train,y_train],axis=1)
+    plt.scatter
 
 
 
+
+c = visualise_data(data,figname = 'data/student-mat.csv')
+
+
+
+
diff --git a/q04_data_visualisation/tests/__pycache__/__init__.cpython-36.pyc b/q04_data_visualisation/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_data_visualisation/tests/__pycache__/test.cpython-36.pyc b/q04_data_visualisation/tests/__pycache__/test.cpython-36.pyc
diff --git a/q05_linear_regression_model/__pycache__/__init__.cpython-36.pyc b/q05_linear_regression_model/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_linear_regression_model/__pycache__/build.cpython-36.pyc b/q05_linear_regression_model/__pycache__/build.cpython-36.pyc
diff --git a/q05_linear_regression_model/build.py b/q05_linear_regression_model/build.py
@@ -1,3 +1,4 @@
+# %load q05_linear_regression_model/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
@@ -11,5 +12,13 @@
 x_train, x_test = label_encode(x_train,x_test)
 
 
-# Write your code below
-
+def linear_regression(x_train,y_train):
+    linreg = LinearRegression()
+    model1 = linreg.fit(x_train,y_train)
+    return model1
+
+
+c=linear_regression(x_train,y_train)
+c
+
+
diff --git a/q05_linear_regression_model/tests/__pycache__/__init__.cpython-36.pyc b/q05_linear_regression_model/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_linear_regression_model/tests/__pycache__/test.cpython-36.pyc b/q05_linear_regression_model/tests/__pycache__/test.cpython-36.pyc
diff --git a/q06_cross_validation/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_cross_validation/__pycache__/build.cpython-36.pyc b/q06_cross_validation/__pycache__/build.cpython-36.pyc
diff --git a/q06_cross_validation/build.py b/q06_cross_validation/build.py
@@ -1,10 +1,11 @@
+# %load q06_cross_validation/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
 from greyatomlib.multivariate_regression_project.q05_linear_regression_model.build import linear_regression
 
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
-
+from sklearn.linear_model import LinearRegression
 from sklearn.model_selection import cross_val_score
 from sklearn.model_selection import KFold
 import numpy as np
@@ -16,6 +17,13 @@
 x_train,x_test = label_encode(x_train,x_test)
 
 model =linear_regression(x_train,y_train)
+linreg = LinearRegression()
+def cross_validation_regressor(model,x_test,y_train):
+    score = cross_val_score(linreg,x_train,y_train)
+    return score.mean()
+
+c=cross_validation_regressor(model,x_test,y_train)
+c
+
+
 
-# Write your code below
-
diff --git a/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_cross_validation/tests/__pycache__/test.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/test.cpython-36.pyc
diff --git a/q07_regression_pred/__pycache__/__init__.cpython-36.pyc b/q07_regression_pred/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_regression_pred/__pycache__/build.cpython-36.pyc b/q07_regression_pred/__pycache__/build.cpython-36.pyc
diff --git a/q07_regression_pred/build.py b/q07_regression_pred/build.py
@@ -1,3 +1,4 @@
+# %load q07_regression_pred/build.py
 
 from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
 
@@ -18,5 +19,14 @@
 
 val = cross_validation_regressor(model,x_train,y_train)
 
+def regression_predictor(model,x_test,y_train):
+    y_pred = model.predict(x_test)
+    mse = mean_squared_error(y_test,y_pred)
+    mae = mean_absolute_error(y_test,y_pred)
+    r2 = model.score(x_test,y_test)
+    return y_pred,mse,mae,r2
+
+c=regression_predictor(model,x_test,y_train)
+c
+
 
-# Write your code below    
diff --git a/q07_regression_pred/tests/__pycache__/__init__.cpython-36.pyc b/q07_regression_pred/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_regression_pred/tests/__pycache__/test.cpython-36.pyc b/q07_regression_pred/tests/__pycache__/test.cpython-36.pyc
diff --git a/q08_linear_model/__pycache__/__init__.cpython-36.pyc b/q08_linear_model/__pycache__/__init__.cpython-36.pyc
diff --git a/q08_linear_model/__pycache__/build.cpython-36.pyc b/q08_linear_model/__pycache__/build.cpython-36.pyc
diff --git a/q08_linear_model/build.py b/q08_linear_model/build.py
@@ -1,3 +1,4 @@
+# %load q08_linear_model/build.py
 import pandas as pd
 import numpy as np
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
@@ -15,6 +16,15 @@
 val = cross_validation_regressor(model,x_train,y_train)
 y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
 
-# Write your code below
+def linear_model(x_train,x_test,y_train,y_test):
+    rmse = np.sqrt(mse)
+    stats = pd.DataFrame({'cross_validation':val,
+                         'mse':mse,'mae':mae,'r2':r2},index=['name'])
+    return model,y_pred,stats
 
 
+
+c = linear_model(x_train,x_test,y_train,y_test)
+c
+
+
diff --git a/q08_linear_model/tests/__pycache__/__init__.cpython-36.pyc b/q08_linear_model/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q08_linear_model/tests/__pycache__/test.cpython-36.pyc b/q08_linear_model/tests/__pycache__/test.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q01_lasso/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/__pycache__/build.cpython-36.pyc b/q09_advanced_model_q01_lasso/__pycache__/build.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/build.py b/q09_advanced_model_q01_lasso/build.py
@@ -1,3 +1,4 @@
+# %load q09_advanced_model_q01_lasso/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
@@ -8,16 +9,28 @@
 from sklearn.linear_model import Lasso
 import numpy as np
 import pandas as pd
-
+from sklearn.metrics import mean_absolute_error,mean_squared_error
 from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor
 np.random.seed(9)
-
+from sklearn.model_selection import cross_val_score
 df = load_data('data/student-mat.csv')
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your solution here
+def lasso(x_train,x_test,y_train,y_test,alpha=0.1):
+    lass = Lasso(alpha=0.1,random_state=9)
+    model = lass.fit(x_train,y_train)
+    y_pred = model.predict(x_test)
+    mse = mean_squared_error(y_test,y_pred)
+    mae = mean_absolute_error(y_test,y_pred)
+    rmse = np.sqrt(mse)
+    val = cross_val_score(lass,x_train,y_train)
+    stats = pd.DataFrame({'cross_validation':val.mean(),
+                         'rmse':rmse,'mae':mae,'r2':(model.score(x_test,y_test))},index=['name'])
+    return model,y_pred,stats
+c=lasso(x_train,x_test,y_train,y_test,alpha=0.1)
+c
+
 
-
diff --git a/q09_advanced_model_q01_lasso/tests/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q01_lasso/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/tests/__pycache__/test.cpython-36.pyc b/q09_advanced_model_q01_lasso/tests/__pycache__/test.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q02_ridge/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/__pycache__/build.cpython-36.pyc b/q09_advanced_model_q02_ridge/__pycache__/build.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/build.py b/q09_advanced_model_q02_ridge/build.py
@@ -1,3 +1,4 @@
+# %load q09_advanced_model_q02_ridge/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
@@ -8,18 +9,35 @@
 from sklearn.linear_model import Ridge
 import numpy as np
 import pandas as pd
+from sklearn.model_selection import cross_val_score
+from sklearn.metrics import mean_absolute_error,mean_squared_error
 
 from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor
-np.random.seed(9)
+
 
 df = load_data('data/student-mat.csv')
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your code below
+def ridge(x_train,x_test,y_train,y_test,alpha=0.1):
+    rid = Ridge(alpha=0.1,random_state=9,normalize=True)
+    model = rid.fit(x_train,y_train)
+    y_pred = model.predict(x_test)
+    mse = mean_squared_error(y_test,y_pred)
+    mae = mean_absolute_error(y_test,y_pred)
+    rmse = np.sqrt(mse)
+    val = cross_val_score(rid,x_train,y_train)
+    stats = pd.DataFrame({'cross_validation':val.mean(),
+                         'rmse':rmse,'mae':mae,'r2':model.score(x_test,y_test)},index=['name'])
+    return model,y_pred,stats
 
 
 
 
+
+c=ridge(x_train,x_test,y_train,y_test,alpha=0.1)
+c
+
+
diff --git a/q09_advanced_model_q02_ridge/tests/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q02_ridge/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/tests/__pycache__/test.cpython-36.pyc b/q09_advanced_model_q02_ridge/tests/__pycache__/test.cpython-36.pyc
diff --git a/q10_data_missing_values/__pycache__/__init__.cpython-36.pyc b/q10_data_missing_values/__pycache__/__init__.cpython-36.pyc
diff --git a/q10_data_missing_values/__pycache__/build.cpython-36.pyc b/q10_data_missing_values/__pycache__/build.cpython-36.pyc
diff --git a/q10_data_missing_values/build.py b/q10_data_missing_values/build.py
@@ -1,3 +1,4 @@
+# %load q10_data_missing_values/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
@@ -9,5 +10,12 @@
 x_train, x_test, y_train, y_test =  split_dataset(df)
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your code below
+def describe_df(df):
+    a=x_train.apply(pd.value_counts)
+    b=x_train.describe()
+    return b,a
 
+
+
+
+
diff --git a/q10_data_missing_values/tests/__pycache__/__init__.cpython-36.pyc b/q10_data_missing_values/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q10_data_missing_values/tests/__pycache__/test.cpython-36.pyc b/q10_data_missing_values/tests/__pycache__/test.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/build.py b/q11_feature_selection_q01_plot_corr/build.py
@@ -1,11 +1,14 @@
+# %load q11_feature_selection_q01_plot_corr/build.py
 
 import matplotlib.pyplot as plt
 from matplotlib.pyplot import yticks, xticks, subplots, set_cmap
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
-
-
+import seaborn as sns
+import matplotlib
+# matplotlib.use('Agg')
+plt.switch_backend('agg')
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
-
+import pandas as pd
 
 
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
@@ -14,13 +17,23 @@
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 x_train,x_test = label_encode(x_train,x_test)
-
+x_train = pd.concat([x_train,y_train],axis=1)
 
 # =============================================================================
 # To visualise data, you need to pass training data only as the assumption holds that test set is unknown data and obviously,you cant not make decision based on unseen data :-p
 
 #Remember to concatenate training features and labels if you want to check that scatterplots which I would prefer.You are free to explore labels to labels, features to features ,etc scatterplots as you want by passing arguments
 #============================================================================
-#visualise_data(pd.concat([x_train,y_train],axis=1),"../images/data_image.png")
+#visualise_data(pd.concat([x_train,y_train],axis=1),'../images/data_image.png')
+
+def plot_corr(df,size=11):
+    numeric = x_train._get_numeric_data()
+    train = pd.concat([numeric,pd.DataFrame(y_train)],1)
+    cor_numeric = train.corr()
+    sns.heatmap(cor_numeric)
+    plt.set_cmap('YlOrRd')
+
+plot_corr(df,size=11)
+plot_corr(df,size=11)
+
 
-# Write your solution here:
diff --git a/q11_feature_selection_q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/tests/__pycache__/test.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/tests/__pycache__/test.cpython-36.pyc
diff --git a/q11_feature_selection_q02_best_k_features/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q02_best_k_features/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/__pycache__/build.cpython-36.pyc