Commit Live PR

q01_load_data/build.py

@@ -1,9 +1,19 @@
+# %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"
+# 'write your solution here'
 
+def q01_load_data(path):
+    df = pd.read_csv(path)
+    df.reset_index(drop=True, inplace=True)
+    return df
+
+# q01_load_data(path)
+
+
+
 

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
@@ -6,4 +7,17 @@
 #sys.path.append('./')
 from greyatomlib.time_series_101_project.q01_load_data.build import q01_load_data
 
-'''Write your solution here'''
+path = 'data/perrin-freres-monthly-champagne.csv'
+
+# '''Write your solution here'''
+
+def q02_data_splitter(path):
+    df = q01_load_data(path)
+    df['Month'] = pd.to_datetime(df['Month'])
+    split_date = pd.datetime(1971,10,1)
+    X_train = df[df['Month'] < split_date]
+    X_valid = df[df['Month'] >=split_date]
+    return X_train,X_valid
+
+
+

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 +9,27 @@
 plt.switch_backend('agg')
 import seaborn as sns
 
-#"write your solution here"
+#'write your solution here'
 
+path = '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']
+
+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_valid = q02_data_splitter(path)
+    X_train['year']  = X_train['Month'].dt.year
+    X_train['month'] = X_train['Month'].dt.strftime('%b')
+    plt.figure(figsize=(16, 7))
+    sns.pointplot(x=x_column_name, y=y_column_name, hue=hue, data=X_train, x_order=order_of_the_axis)
+    plt.xlabel('month')
+    plt.ylabel('sales')
+    plt.legend(title='year',loc='upper left')
+    plt.show()
+
+# q03_stacked_point_plot(path,x_column_name,y_column_name,hue,order_of_the_axis)
+
+
+

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 +10,30 @@
 # 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'
 
+path = 'data/perrin-freres-monthly-champagne.csv'
+x ='month'
+y ='Sales'
+kind = 'box'
+order = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug','Sep', 'Oct', 'Nov', 'Dec']
+size = 8
+
+def q04_boxplot(path,x='month',y='Sales',kind='box',
+                order=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug','Sep', 'Oct', 'Nov', 'Dec'],size=8):
+
+    X_train,X_valid = q02_data_splitter(path)
+    X_train['month'] = X_train['Month'].dt.strftime('%b')
+    X_train['year'] = X_train['Month'].dt.year
+    plt.figure(figsize=(16,7))
+    sns.factorplot(x=x,y=y,data=X_train,kind=kind,order=order,size=size)
+    plt.xlabel('Month')
+    plt.ylabel('Sales')
+    plt.title('Monthly Sales')
+    plt.show()
+
+# q04_boxplot(path,x,y,kind,order,size)
+
+
+
 

q05_sarima_model/build.py

@@ -1,14 +1,38 @@
+# %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 sys
 # sys.path.append('./')
+
+path = 'data/perrin-freres-monthly-champagne.csv'
+
 from greyatomlib.time_series_101_project.q02_data_splitter.build import q02_data_splitter
-train, validation = q02_data_splitter(path)
 
+#train, validation = q02_data_splitter(path)
+
+'write your solution here'
+
+def q05_sarima_model(path):
+
+    train, validation = q02_data_splitter(path)
+    train = pd.DataFrame(train)
+    validation = pd.DataFrame(validation)
 
-"write your solution here"
+    tss = pd.DataFrame(train['Sales'])
+    tss.column = ['Sales']
+    tss.index = train['Month'].values
 
+    tss_valid = pd.DataFrame(validation['Sales'])
+    tss_valid.column = ['Sales']
+    tss_valid.index = validation['Month'].values
+
+    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
@@ -7,10 +8,28 @@
 from statsmodels.tsa.statespace import sarimax
 import math
 from sklearn.metrics import mean_squared_error
-#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"
+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
+
+    measure = math.pow(mean_squared_error(tss_valid.values, pred.values), 0.5)
+
+    return pred, measure
+
+# q06_sarima_predictor(path)
 
+
+
+