Commit Live PR

q01_load_data/build.py

@@ -1,9 +1,14 @@
+# %load q01_load_data/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 
-path = 'data/perrin-freres-monthly-champagne.csv
+path = 'data/perrin-freres-monthly-champagne.csv'
+
+'write your solution here'
+def q01_load_data(path):
+    df = pd.read_csv(path)
+    return df
+q01_load_data(path)
 
-"write your solution here"
-
 

q02_data_splitter/build.py

@@ -1,3 +1,4 @@
+# %load q02_data_splitter/build.py
 import pandas as pd
 import numpy as np
 import datetime
@@ -7,3 +8,12 @@
 from greyatomlib.time_series_101_project.q01_load_data.build import q01_load_data
 
 '''Write your solution here'''
+def q02_data_splitter(path):
+    df = q01_load_data(path)
+    df['Month'] = pd.to_datetime(df['Month'])
+    X_train = df[df['Month']<'1971-10-01']
+    X_test = df[df['Month']>='1971-10-01']
+    return X_train,X_test
+q02_data_splitter( 'data/perrin-freres-monthly-champagne.csv')
+
+

q03_stacked_point_plot/build.py

@@ -1,3 +1,4 @@
+# %load q03_stacked_point_plot/build.py
 import pandas as pd
 import numpy as np
 #import sys
@@ -8,5 +9,15 @@
 plt.switch_backend('agg')
 import seaborn as sns
 
-#"write your solution here"
-
+#'write your solution here'
+def q03_stacked_point_plot(path,x_column_name='month',y_column_name='Sales',hue='year',order_of_the_axis=['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']):
+    X_train,X_test = q02_data_splitter(path)
+    X_train['month'] = X_train['Month'].dt.strftime('%b')
+    X_train['year'] = X_train['Month'].dt.year
+    sns.pointplot(
+        x=x_column_name,y=y_column_name,hue=hue,data=X_train,x_order=order_of_the_axis
+    )
+    plt.show()
+q03_stacked_point_plot('data/perrin-freres-monthly-champagne.csv',x_column_name='month',y_column_name='Sales',hue='year',order_of_the_axis=['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec'])
+
+

q04_boxplot/build.py

@@ -1,3 +1,4 @@
+# %load q04_boxplot/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
@@ -9,6 +10,12 @@
 # sys.path.append('./')
 from greyatomlib.time_series_101_project.q02_data_splitter.build import q02_data_splitter
 
-"write your solution here"
-
+'write your solution here'
+def q04_boxplot(path,x='month',y='Sales',kind='box',order_of_the_axis=['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec'],temp=8):
+    X_train,X_test = q02_data_splitter(path)
+    X_train['month'] = X_train['Month'].dt.strftime('%b')
+    X_train['year'] = X_train['Month'].dt.year
+    sns.factorplot(x=x,y=y,data=X_train,kind=kind)
+    plt.show()
+
 

q05_sarima_model/build.py

@@ -1,14 +1,27 @@
+# %load q05_sarima_model/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 import seaborn as sns
 import matplotlib.pyplot as plt
+import datetime
 # import sys
 # sys.path.append('./')
 from greyatomlib.time_series_101_project.q02_data_splitter.build import q02_data_splitter
+path='data/perrin-freres-monthly-champagne.csv'
 train, validation = q02_data_splitter(path)
 
 
-"write your solution here"
-
+'write your solution here'
+def q05_sarima_model(path):
+    df = pd.read_csv(path)
+    df['Month']=pd.to_datetime(df['Month'])
+    df = df.set_index('Month')
+    tss = df[:93]
+    tss_valid = df[93:]
+    tss.index.names = [None]
+    tss_valid.index.names = [None]
+    return tss,tss_valid
+q05_sarima_model(path)
+
 

q06_sarima_predictor/build.py

@@ -1,3 +1,4 @@
+# %load q06_sarima_predictor/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
@@ -10,7 +11,27 @@
 #import sys
 #sys.path.append('./')
 from greyatomlib.time_series_101_project.q05_sarima_model.build import q05_sarima_model
+path = 'data/perrin-freres-monthly-champagne.csv'
 tss, tss_valid = q05_sarima_model(path)
 
-    "write your solution here"
-
+'write your solution here'
+def q06_sarima_predictor(path):
+    mod = sarimax.SARIMAX(tss['Sales'], order=(5, 1, 1), seasonal_order=(1, 1, 0, 12)).fit()
+    plt.figure(figsize=(16, 7))
+    plt.plot(tss.index, tss.Sales, color='lightblue')
+    plt.plot(tss_valid.index, tss_valid.Sales.values, color='green')
+
+    ## Forecasting
+    pred = pd.DataFrame(mod.forecast(len(tss_valid)))
+    pred.columns = ['yhat']
+    pred.index = tss_valid.index
+
+    ## Converting from log to normal value
+    # pred['yhat'] = pred['yhat'].apply(lambda x: int(math.exp(x)-1))
+
+    ## Measuring error.
+    measure = math.pow(mean_squared_error(tss_valid.values, pred.values), 0.5)
+    return pred, measure
+q06_sarima_predictor(path)
+
+