Commit Live PR

q01_load_data/build.py

@@ -1,7 +1,12 @@
+# %load q01_load_data/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 
+def q01_load_data(path):
+    df = pd.read_csv(path)
+    df['Datetime'] = pd.to_datetime(df['Datetime'])
+    return df.shape,df
+q01_load_data('data/elecdemand.csv')
 
 
-

q02_data_splitter/build.py

@@ -1,7 +1,16 @@
+# %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
 
+def q02_data_splitter(path):
+    np.random.seed(9)
+    df_shape,df = q01_load_data(path)
+    time_series_Split = TimeSeriesSplit(n_splits=2)
+    train = time_series_Split.split(X=df)
+    return list(train)
+
+q02_data_splitter('data/elecdemand.csv')
+
 
-

q03_time_plot/build.py

@@ -1,7 +1,14 @@
+# %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')
+import datetime
+
+def q03_time_plot(path):
+    df_shape,df = q01_load_data(path)
+    plt.plot(df['Datetime'],df['Demand'])
+q03_time_plot('data/elecdemand.csv')
 
 

q04_boxplot/build.py

@@ -1,7 +1,15 @@
+# %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')
+
 
-

q05_feature_engineering/build.py

@@ -1,9 +1,14 @@
+# %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')
 
+def q05_feature_engineering(path):
+    df_shape,df = q01_load_data(path)
+    plt.scatter(df['Temperature'],df['Demand'])
 
+q05_feature_engineering('data/elecdemand.csv')
 
 

q05_feature_engineering_part2/build.py

@@ -1,8 +1,18 @@
+# %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 
+from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data
 plt.switch_backend('agg')
 
+def q05_feature_engineering_part2(path):
+    df_shape, df = q01_load_data(path)
+    df['hour'] = df['Datetime'].dt.hour
+    hours = []
+    for i in range(24):
+        one = df[df['hour'] == i]['Demand'].values
+        hours.append(one)
+    plt.boxplot(hours, labels=[str(i) for i in range(24)])
+    plt.show()
+
 
-

q05_feature_engineering_part3/build.py

@@ -1,8 +1,19 @@
+# %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')
+
 
-

q05_feature_engineering_part4/build.py

@@ -1,9 +1,17 @@
+# %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():    
-
+def q05_feature_engineering_part4(path):
+    df_shape,df = q01_load_data(path)
+    df['hour'] = df['Datetime'].dt.hour
+    df['month'] = df['Datetime'].dt.strftime('%b')
+    df['Peakhours'] = ((df['hour']>=6) & (df['hour']<20))*1
+    df['Peakmonths'] = df['month'].apply(lambda x : 1 if x in ['Feb', 'May', 'Jun', 'Jul', 'Aug'] else 0)
+    return df
+q05_feature_engineering_part4('data/elecdemand.csv')
+
+

q06_linear_regression/build.py

@@ -1,12 +1,34 @@
+# %load q06_linear_regression/build.py
 import pandas as pd
 import numpy as np
 import math
 from sklearn.linear_model import LinearRegression
 from sklearn.metrics import mean_squared_error
 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
+from greyatomlib.time_series_day_02_project.q01_load_data.build import q01_load_data
 
-fe =  ["WorkDay", "Peakhours", "Peakmonths"]
-
+fe =  ['WorkDay', 'Peakhours', 'Peakmonths']
 
+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)
+    'write your solution here'
 
+    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)
+
+
+
+

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']
 
+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)
+    'write your solution here'
+
+    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('data/elecdemand.csv',columns = fe, random_state =9)
 
+
+
+

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 +7,26 @@
 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']
+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)
+    'write your solution here'
+
+    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('data/elecdemand.csv',columns = fe, random_state =9)
+
+