From 2d8c2135e61d8fd8c59461ecae528d7026fd89f8 Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Thu, 13 Dec 2018 03:27:02 +0000 Subject: [PATCH 01/10] Done --- q01_load_data/build.py | 11 ++++++++++- q01_load_data/tests/test_sol.pkl | Bin 0 -> 79 bytes q01_load_data/tests/user_sol.pkl | Bin 0 -> 67 bytes q02_data_splitter/build.py | 13 +++++++++++++ q02_data_splitter/tests/test_sol.pkl | Bin 0 -> 87 bytes q02_data_splitter/tests/user_sol.pkl | Bin 0 -> 75 bytes 6 files changed, 23 insertions(+), 1 deletion(-) create mode 100644 q01_load_data/tests/test_sol.pkl create mode 100644 q01_load_data/tests/user_sol.pkl create mode 100644 q02_data_splitter/tests/test_sol.pkl create mode 100644 q02_data_splitter/tests/user_sol.pkl diff --git a/q01_load_data/build.py b/q01_load_data/build.py index a29c139..a0dfed8 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,7 +1,16 @@ +# %load q01_load_data/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split +path ='data/elecdemand.csv' + +def q01_load_data(path): + data = pd.read_csv(path) + data['Datetime']=pd.to_datetime(data['Datetime']) + return data.shape, data + +# q01_load_data(path) + - diff --git a/q01_load_data/tests/test_sol.pkl b/q01_load_data/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7912fb668f4a4bff9f60d47546462bb183207435 GIT binary patch literal 79 zcmZo*PEIdMtxPP*&&|n9(ksc#O^q*3Ey_$Sj!#Lfj5jcfFDS~-N=+`&D>N{S&&f|r W0g9I->LrzC=A>|;h;bD%=m7w&xE!N{S&&f|r0g9I->LrzC=A>|; Kh;bD%=m7vu+!yBn literal 0 HcmV?d00001 diff --git a/q02_data_splitter/build.py b/q02_data_splitter/build.py index b6c715f..595f15a 100644 --- a/q02_data_splitter/build.py +++ b/q02_data_splitter/build.py @@ -1,7 +1,20 @@ +# %load q02_data_splitter/build.py import pandas as pd import numpy as np from sklearn.model_selection import TimeSeriesSplit from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data +path = 'data/elecdemand.csv' +def q02_data_splitter(path): + np.random.seed(9) + shape,data = q01_load_data(path) + tscv = TimeSeriesSplit(n_splits=2) + split_data = list(tscv.split(data)) + return split_data +# q02_data_splitter(path) + + + + diff --git a/q02_data_splitter/tests/test_sol.pkl b/q02_data_splitter/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a3e9cc57e21382b4149f86a10e44fd859a5d4213 GIT binary patch literal 87 zcmZo*PEIdMtxPP*&&|n9(ksc#O^q*3Ey_$Sj!#Lfj5jcfFDS~-N=+`&D+IDr5=#=} ZiwklxOG;9U^pZ+5b5gi4#JLI?^Z>TKAY=dl literal 0 HcmV?d00001 diff --git a/q02_data_splitter/tests/user_sol.pkl b/q02_data_splitter/tests/user_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..70c23336a7d13cc99ae68a1dcdbdc3e6646e261a GIT binary patch literal 75 zcmZo*PA Date: Thu, 13 Dec 2018 03:31:07 +0000 Subject: [PATCH 02/10] Done --- q03_time_plot/build.py | 16 ++++++++++++++++ test_sol.pkl | Bin 0 -> 79 bytes user_sol.pkl | Bin 0 -> 67 bytes 3 files changed, 16 insertions(+) create mode 100644 test_sol.pkl create mode 100644 user_sol.pkl diff --git a/q03_time_plot/build.py b/q03_time_plot/build.py index bf18743..e123866 100644 --- a/q03_time_plot/build.py +++ b/q03_time_plot/build.py @@ -1,7 +1,23 @@ +# %load q03_time_plot/build.py import pandas as pd import numpy as np import matplotlib.pyplot as plt from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data plt.switch_backend('agg') +path = 'data/elecdemand.csv' + +def q03_time_plot(path): + shp,df=q01_load_data(path) + plt.figure(figsize=(16, 6)) + plt.plot(df['Datetime'], df['Demand']) + plt.xlabel('Time') + plt.ylabel('Demand') + plt.title('Electricity Demand in Australia for a year') + plt.show() + +# q03_time_plot(path) + + + diff --git a/test_sol.pkl b/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cec104b8f2d3d8445aa4256f364f0ca31036739d GIT binary patch literal 79 zcmZo*PEIdMtxPP*&&|n9(ksc#O^q*3Ey_$Sj!#Lfj5jcfFDS~-N=+`&D>N{U2TK>^ UN{U2TK>^ Date: Thu, 13 Dec 2018 03:35:14 +0000 Subject: [PATCH 03/10] Done --- q05_feature_engineering/build.py | 17 +++++++++++++++++ q05_feature_engineering/tests/test_sol.pkl | Bin 0 -> 99 bytes q05_feature_engineering/tests/user_sol.pkl | Bin 0 -> 87 bytes 3 files changed, 17 insertions(+) create mode 100644 q05_feature_engineering/tests/test_sol.pkl create mode 100644 q05_feature_engineering/tests/user_sol.pkl diff --git a/q05_feature_engineering/build.py b/q05_feature_engineering/build.py index 97e29e7..3b0cc90 100644 --- a/q05_feature_engineering/build.py +++ b/q05_feature_engineering/build.py @@ -1,9 +1,26 @@ +# %load q05_feature_engineering/build.py import pandas as pd import numpy as np import matplotlib.pyplot as plt from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data plt.switch_backend('agg') +path='data/elecdemand.csv' + +def q05_feature_engineering(path): + shape,df = q01_load_data(path) + corr=np.corrcoef(df['Temperature'], df['Demand']) + plt.figure(figsize=(16, 6)) + plt.scatter(df['Temperature'], df['Demand']) + plt.xlabel('Temperature') + plt.ylabel('Demand') + plt.title('Temperature vs Demand') + plt.show() + +# q05_feature_engineering(path) + + + diff --git a/q05_feature_engineering/tests/test_sol.pkl b/q05_feature_engineering/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c8990f6faf7b3093f4ad2a9063625b47c6c393dd GIT binary patch literal 99 zcmZ|F$q9fk5Cu@do5c)4u%02yH;iO4+aWhg*9JVl_pH`eOx<$~VyH_5H&j7mrzfkO e@0u^zPDLGjLibU@NL~`YmOPmu!EHafm4#kvmnAj; literal 0 HcmV?d00001 diff --git a/q05_feature_engineering/tests/user_sol.pkl b/q05_feature_engineering/tests/user_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9f2b9eccc8898617f94e628a44c1bb332af295e3 GIT binary patch literal 87 zcmZo*PAN{TPfJZKDJ@EkPt8lu%u59- U%S+cwD$UGE;ld%yRmh+R0IR4VX#fBK literal 0 HcmV?d00001 From 7066ff8f880263b4f173b87f8c2705c81ed3f6f0 Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Thu, 13 Dec 2018 03:44:45 +0000 Subject: [PATCH 04/10] Done --- q05_feature_engineering_part2/build.py | 38 +++++++++++++++++- .../tests/test_sol.pkl | Bin 0 -> 111 bytes .../tests/user_sol.pkl | Bin 0 -> 99 bytes q05_feature_engineering_part4/build.py | 20 +++++++-- .../tests/test_sol.pkl | Bin 0 -> 111 bytes .../tests/user_sol.pkl | Bin 0 -> 99 bytes 6 files changed, 52 insertions(+), 6 deletions(-) create mode 100644 q05_feature_engineering_part2/tests/test_sol.pkl create mode 100644 q05_feature_engineering_part2/tests/user_sol.pkl create mode 100644 q05_feature_engineering_part4/tests/test_sol.pkl create mode 100644 q05_feature_engineering_part4/tests/user_sol.pkl diff --git a/q05_feature_engineering_part2/build.py b/q05_feature_engineering_part2/build.py index 53e6749..f3bcb83 100644 --- a/q05_feature_engineering_part2/build.py +++ b/q05_feature_engineering_part2/build.py @@ -1,8 +1,42 @@ +# %load q05_feature_engineering_part2/build.py import pandas as pd import numpy as np import matplotlib.pyplot as plt -from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data -plt.switch_backend('agg') +from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data +path = 'data/elecdemand.csv' +# def q05_feature_engineering_part2(path): +# shape, data = q01_load_data(path) +# 'write your solution here' +# data['hour'] = data['Datetime'].dt.hour + +# plt.figure(figsize=(16, 6)) + +# hours = [] +# for i in range(24): +# one = data[data['hour'] == i]['Demand'].values +# hours.append(one) +# plt.boxplot(hours, labels=[str(i) for i in range(24)]) +# plt.xlabel('Hour') +# plt.ylabel('Demand') +# plt.title('Change in Electricity demand wrt to Hour') +# plt.show() + +def q05_feature_engineering_part2(path): + shape, data = q01_load_data(path) + 'write your solution here' + data['hour'] = data['Datetime'].dt.hour + plt.figure(figsize=(16, 6)) + hours = [] + for i in range(24): + one = data[data['hour'] == i]['Demand'].values + hours.append(one) + plt.boxplot(hours, labels=[str(i) for i in range(24)]) + plt.xlabel('Hour') + plt.ylabel('Demand') + plt.title('Change in Electricity demand wrt to Hour') +# q05_feature_engineering_part2(path) + + diff --git a/q05_feature_engineering_part2/tests/test_sol.pkl b/q05_feature_engineering_part2/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2f666a14df1eb6caf5167db48841dd663be1e31b GIT binary patch literal 111 zcmaLNO%6an3N{TPfJZKDJ@EkPt8lu%u59- a%S(?hNGvKb(n~7M%t_(GtA?wPK@R{~@Fe*F literal 0 HcmV?d00001 diff --git a/q05_feature_engineering_part4/build.py b/q05_feature_engineering_part4/build.py index 2731397..cdc86bb 100644 --- a/q05_feature_engineering_part4/build.py +++ b/q05_feature_engineering_part4/build.py @@ -1,9 +1,21 @@ +# %load q05_feature_engineering_part2/build.py import pandas as pd import numpy as np -from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data -plt.switch_backend('agg') -def q05_feature_engineering_part4(): - +path='data/elecdemand.csv' + +def q05_feature_engineering_part4(path): + shape, data = q01_load_data(path) + data['hour'] = data['Datetime'].dt.hour + data['month'] = data['Datetime'].dt.strftime('%b') + data['Peakhours']=data['hour'].apply(lambda x : 1 if x in range(6,20) else 0) + data['Peakmonths']=data['month'].apply(lambda x : 1 if x in ['Feb', 'May', 'Jun', 'Jul', 'Aug'] else 0) + return data + +# q05_feature_engineering_part4(path) + + + + diff --git a/q05_feature_engineering_part4/tests/test_sol.pkl b/q05_feature_engineering_part4/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..fca58170afc11aa0ba91572679fb87f1db092e35 GIT binary patch literal 111 zcmaLNO%6an3N{TPfJZKDJ@EkPt8lu%u59- a%S(?hNGvKb(Mu}L%t_(GtA?wPK@R|0OeFmP literal 0 HcmV?d00001 From dc6844ab383502d4f8bbf52fbff43da576e58553 Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Thu, 13 Dec 2018 04:07:01 +0000 Subject: [PATCH 05/10] Done --- q06_linear_regression/build.py | 24 ++++++++++++++++++++++- q06_linear_regression/tests/test_sol.pkl | Bin 0 -> 95 bytes q06_linear_regression/tests/user_sol.pkl | Bin 0 -> 83 bytes 3 files changed, 23 insertions(+), 1 deletion(-) create mode 100644 q06_linear_regression/tests/test_sol.pkl create mode 100644 q06_linear_regression/tests/user_sol.pkl diff --git a/q06_linear_regression/build.py b/q06_linear_regression/build.py index 8c11052..cbe9f6e 100644 --- a/q06_linear_regression/build.py +++ b/q06_linear_regression/build.py @@ -1,3 +1,4 @@ +# %load q06_linear_regression/build.py import pandas as pd import numpy as np import math @@ -6,7 +7,28 @@ from greyatomlib.time_series_day_02_project.q05_feature_engineering_part4.build import q05_feature_engineering_part4 from greyatomlib.time_series_day_02_project.q02_data_splitter.build import q02_data_splitter -fe = ["WorkDay", "Peakhours", "Peakmonths"] +fe = ['WorkDay', 'Peakhours', 'Peakmonths'] +path = 'data/elecdemand.csv' +def q06_linear_regression(path,columns = fe, random_state =9): + np.random.seed(random_state) + data = q05_feature_engineering_part4(path) + splits = q02_data_splitter(path) + rmse = [] + for i in splits: + train = i[0] + valid = i[1] + x_train, y_train = data[fe].values[train], data['Demand'].values[train] + x_valid, y_valid = data[fe].values[valid], data['Demand'].values[valid] + model = LinearRegression() + model.fit(x_train, y_train) + pred = model.predict(x_valid) + measure = math.pow(mean_squared_error(y_valid, pred), 0.5) + rmse.append(measure) + return np.mean(rmse) + + + + diff --git a/q06_linear_regression/tests/test_sol.pkl b/q06_linear_regression/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e0cbf28ec8ae05c55b655d1ba771b898848292f2 GIT binary patch literal 95 zcmZo*PEIdMtxPP*&&|n9(ksc#O^q*3Ey_$Sj!#Lfj5jcfFDS~-N=+`&D>N{R&&kY7 eO)QEpN(JgEF3!x)(@QGN%t_(GD#umGpa%ffmLtLd literal 0 HcmV?d00001 diff --git a/q06_linear_regression/tests/user_sol.pkl b/q06_linear_regression/tests/user_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..6794af11eb97c6033013830c6dee62f85f8732a4 GIT binary patch literal 83 zcmZo*PAN{R&&kY7O)QEpN=+|HEiTT? T&(ljP&CE&R!YapA$e;%RD(W8f literal 0 HcmV?d00001 From e999a16abd66fc5d7e7bd2c10ad44a2c213ff953 Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Thu, 13 Dec 2018 04:08:56 +0000 Subject: [PATCH 06/10] Done --- q07_randomforest_regressor/build.py | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/q07_randomforest_regressor/build.py b/q07_randomforest_regressor/build.py index 4cdb470..71a8484 100644 --- a/q07_randomforest_regressor/build.py +++ b/q07_randomforest_regressor/build.py @@ -1,3 +1,4 @@ +# %load q07_randomforest_regressor/build.py import pandas as pd import numpy as np import math @@ -6,7 +7,29 @@ from greyatomlib.time_series_day_02_project.q05_feature_engineering_part4.build import q05_feature_engineering_part4 from greyatomlib.time_series_day_02_project.q02_data_splitter.build import q02_data_splitter -fe = ["WorkDay", "Peakhours", "Peakmonths"] +fe = ['WorkDay', 'Peakhours', 'Peakmonths'] +path = 'data/elecdemand.csv' +def q07_randomforest_regressor(path,columns = fe, random_state =9): + np.random.seed(random_state) + data = q05_feature_engineering_part4(path) + splits = q02_data_splitter(path) + rmse = [] + for i in splits: + train = i[0] + valid = i[1] + x_train, y_train = data[fe].values[train], data['Demand'].values[train] + x_valid, y_valid = data[fe].values[valid], data['Demand'].values[valid] + model = RandomForestRegressor( n_estimators=50, min_samples_leaf=30, random_state=10) + model.fit(x_train, y_train) + pred = model.predict(x_valid) + measure = math.pow(mean_squared_error(y_valid, pred), 0.5) + rmse.append(measure) + return np.mean(rmse) + +# q07_randomforest_regressor(path,columns = fe, random_state =9) + + + From c22893db038755473ba82347b08f835a30fc1269 Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Thu, 13 Dec 2018 04:10:25 +0000 Subject: [PATCH 07/10] Done --- q08_gradientboosting_regressor/build.py | 28 +++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/q08_gradientboosting_regressor/build.py b/q08_gradientboosting_regressor/build.py index e661aac..7c03334 100644 --- a/q08_gradientboosting_regressor/build.py +++ b/q08_gradientboosting_regressor/build.py @@ -1,3 +1,4 @@ +# %load q08_gradientboosting_regressor/build.py import pandas as pd import numpy as np import math @@ -6,5 +7,28 @@ from greyatomlib.time_series_day_02_project.q05_feature_engineering_part4.build import q05_feature_engineering_part4 from greyatomlib.time_series_day_02_project.q02_data_splitter.build import q02_data_splitter -fe = ["WorkDay", "Peakhours", "Peakmonths"] - +fe = ['WorkDay', 'Peakhours', 'Peakmonths'] + +path = 'data/elecdemand.csv' + +def q08_gradientboosting_regressor(path,columns = fe, random_state =9): + np.random.seed(random_state) + data = q05_feature_engineering_part4(path) + splits = q02_data_splitter(path) + rmse = [] + for i in splits: + train = i[0] + valid = i[1] + x_train, y_train = data[fe].values[train], data['Demand'].values[train] + x_valid, y_valid = data[fe].values[valid], data['Demand'].values[valid] + model = GradientBoostingRegressor( n_estimators=200, min_samples_leaf=10, learning_rate=0.01, random_state=random_state) + model.fit(x_train, y_train) + pred = model.predict(x_valid) + measure = math.pow(mean_squared_error(y_valid, pred), 0.5) + rmse.append(measure) + return np.mean(rmse) + +# q08_gradientboosting_regressor(path) + + + From 9e9af61c7b6cd62748b113225e81abe3cccc2e28 Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Fri, 11 Jan 2019 04:00:40 +0000 Subject: [PATCH 08/10] Done --- q04_boxplot/build.py | 12 +++++++++++- q04_boxplot/tests/test_sol.pkl | Bin 0 -> 75 bytes q04_boxplot/tests/user_sol.pkl | Bin 0 -> 63 bytes q05_feature_engineering_part2/build.py | 22 ++-------------------- 4 files changed, 13 insertions(+), 21 deletions(-) create mode 100644 q04_boxplot/tests/test_sol.pkl create mode 100644 q04_boxplot/tests/user_sol.pkl diff --git a/q04_boxplot/build.py b/q04_boxplot/build.py index c69f931..7ed4311 100644 --- a/q04_boxplot/build.py +++ b/q04_boxplot/build.py @@ -1,7 +1,17 @@ +# %load q04_boxplot/build.py + import pandas as pd import numpy as np import matplotlib.pyplot as plt from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data plt.switch_backend('agg') +import seaborn as sns + +def q04_boxplot(path): + df_shape,df = q01_load_data(path) + sns.boxplot(x='WorkDay',y='Demand',data=df) + +# q04_boxplot('data/elecdemand.csv') + + - diff --git a/q04_boxplot/tests/test_sol.pkl b/q04_boxplot/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f863f64a8c994210960bcdfa9c645b392115b34a GIT binary patch literal 75 zcmZo*PEIdMtxPP*&&|n9(ksc#O^q*3Ey_$Sj!#Lfj5jcfFDS~-N=+`&D>N{PPs*<- V$jL9!ODfIGN#Q~g;VNX%0{}mk8<+q9 literal 0 HcmV?d00001 diff --git a/q04_boxplot/tests/user_sol.pkl b/q04_boxplot/tests/user_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..44dda795407bb9cf236e1b00c6328005eb47a0ac GIT binary patch literal 63 zcmZo*PAN{PPs*<-$jL9!ODfIGN#Q~g J;VNX%0|4{i7Rvwt literal 0 HcmV?d00001 diff --git a/q05_feature_engineering_part2/build.py b/q05_feature_engineering_part2/build.py index f3bcb83..b7e6d3f 100644 --- a/q05_feature_engineering_part2/build.py +++ b/q05_feature_engineering_part2/build.py @@ -6,27 +6,8 @@ path = 'data/elecdemand.csv' -# def q05_feature_engineering_part2(path): -# shape, data = q01_load_data(path) -# 'write your solution here' -# data['hour'] = data['Datetime'].dt.hour - -# plt.figure(figsize=(16, 6)) - -# hours = [] -# for i in range(24): -# one = data[data['hour'] == i]['Demand'].values -# hours.append(one) -# plt.boxplot(hours, labels=[str(i) for i in range(24)]) -# plt.xlabel('Hour') -# plt.ylabel('Demand') -# plt.title('Change in Electricity demand wrt to Hour') -# plt.show() - - def q05_feature_engineering_part2(path): shape, data = q01_load_data(path) - 'write your solution here' data['hour'] = data['Datetime'].dt.hour plt.figure(figsize=(16, 6)) hours = [] @@ -36,7 +17,8 @@ def q05_feature_engineering_part2(path): plt.boxplot(hours, labels=[str(i) for i in range(24)]) plt.xlabel('Hour') plt.ylabel('Demand') - plt.title('Change in Electricity demand wrt to Hour') + plt.title('Change in Electricity demand wrt to Hour') + # q05_feature_engineering_part2(path) From 54845b4162d641b9662bea575d1b4d755a0ad8cf Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Fri, 11 Jan 2019 04:04:54 +0000 Subject: [PATCH 09/10] Done --- q05_feature_engineering_part2/build.py | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/q05_feature_engineering_part2/build.py b/q05_feature_engineering_part2/build.py index b7e6d3f..8534b46 100644 --- a/q05_feature_engineering_part2/build.py +++ b/q05_feature_engineering_part2/build.py @@ -3,22 +3,17 @@ import numpy as np import matplotlib.pyplot as plt from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data - -path = 'data/elecdemand.csv' +plt.switch_backend('agg') def q05_feature_engineering_part2(path): - shape, data = q01_load_data(path) - data['hour'] = data['Datetime'].dt.hour - plt.figure(figsize=(16, 6)) + df_shape, df = q01_load_data(path) + df['hour'] = df['Datetime'].dt.hour hours = [] for i in range(24): - one = data[data['hour'] == i]['Demand'].values + one = df[df['hour'] == i]['Demand'].values hours.append(one) plt.boxplot(hours, labels=[str(i) for i in range(24)]) - plt.xlabel('Hour') - plt.ylabel('Demand') - plt.title('Change in Electricity demand wrt to Hour') + plt.show() -# q05_feature_engineering_part2(path) From 4f61e365ca14c8e12eb271725d519158fd65988d Mon Sep 17 00:00:00 2001 From: rajeshbrid Date: Fri, 11 Jan 2019 04:07:06 +0000 Subject: [PATCH 10/10] Done --- q05_feature_engineering_part3/build.py | 15 +++++++++++++++ q05_feature_engineering_part3/tests/test_sol.pkl | Bin 0 -> 111 bytes q05_feature_engineering_part3/tests/user_sol.pkl | Bin 0 -> 99 bytes 3 files changed, 15 insertions(+) create mode 100644 q05_feature_engineering_part3/tests/test_sol.pkl create mode 100644 q05_feature_engineering_part3/tests/user_sol.pkl diff --git a/q05_feature_engineering_part3/build.py b/q05_feature_engineering_part3/build.py index 7da14f7..99050fa 100644 --- a/q05_feature_engineering_part3/build.py +++ b/q05_feature_engineering_part3/build.py @@ -1,8 +1,23 @@ +# %load q05_feature_engineering_part3/build.py + import pandas as pd import numpy as np import matplotlib.pyplot as plt from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data plt.switch_backend('agg') +def q05_feature_engineering_part3(path): + df_shape,df = q01_load_data(path) + df['month'] = df['Datetime'].dt.strftime('%b') + demands=[] + months = ['Jan','Feb','Mar','Apr','Jun','Jul','Aug','Sep','Oct','Nov','Dec'] + for month in months: + temp = df[df['month']==month]['Demand'] + demands.append(list(temp)) + plt.boxplot(demands,labels=months) +q05_feature_engineering_part3('data/elecdemand.csv') + + + diff --git a/q05_feature_engineering_part3/tests/test_sol.pkl b/q05_feature_engineering_part3/tests/test_sol.pkl new file mode 100644 index 0000000000000000000000000000000000000000..017cf665feddbd720b48d7ba68ba334a780efe40 GIT binary patch literal 111 zcmaLNO%6an3N{TPfJZKDJ@EkPt8lu%u59- a%S(?hNGvKb)=MhQ%t_(GtA?wPK@R|09whq! literal 0 HcmV?d00001