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
 
-"write your solution here"
-
+'write your solution here'
+def q01_load_data(path):
+    df = pd.read_csv(path)
+    return df
+
+
 

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 +8,10 @@
 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'] < datetime.datetime(1971,10,1,0,0,0)]
+    X_valid = df[df['Month'] >= datetime.datetime(1971,10,1,0,0,0)]
+    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 +9,19 @@
 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,_ = q02_data_splitter(path)
+
+    X_train['Year'] = X_train['Month'].dt.year
+    X_train['month'] = X_train['Month'].dt.strftime('%b')
+
+    plt.figure(figsize=(16,4))
+    sns.pointplot('month','Sales',hue='Year',data=X_train,order=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug',
+           'Sep', 'Oct', 'Nov', 'Dec'])
+    plt.ylabel('Sales')
+    plt.xlabel('month')
+    plt.legend(loc='upper left')
+    plt.show()
+
+

q04_boxplot/build.py

@@ -1,14 +1,24 @@
+# %load q04_boxplot/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 import matplotlib.pyplot as plt
 plt.switch_backend('agg')
 import seaborn as sns
 import datetime
+
 # import sys
 # 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'],size=8):
+    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, 4))
+    sns.factorplot(x=x, y=y, data=X_train, kind=kind, order=order_of_the_axis, size=size, aspect=float(16/7))
+    plt.xlabel('month')
+    plt.ylabel('Sales')
+
 

q05_sarima_model/build.py

@@ -1,3 +1,4 @@
+# %load q05_sarima_model/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
@@ -6,9 +7,21 @@
 # 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'
+plt.switch_backend('agg')
 train, validation = q02_data_splitter(path)
 
 
-"write your solution here"
-
+'write your solution here'
+def q05_sarima_model(path):
+    train, validation = q02_data_splitter(path)
+    train.index=train['Month']
+    train=train[['Sales']]
+    train.index.name=None
+    validation.index=validation['Month']
+    validation=validation[['Sales']]
+    validation.index.name=None
+    return train,validation
+
+
 

q06_sarima_predictor/build.py

@@ -1,16 +1,33 @@
+# %load q06_sarima_predictor/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
-plt.switch_backend('agg')
 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
-tss, tss_valid = q05_sarima_model(path)
+plt.switch_backend('agg')
+path = 'data/perrin-freres-monthly-champagne.csv'
+
+'write your solution here'
+def q06_sarima_predictor(path):
+    tss, tss_valid = q05_sarima_model(path)
+
+    # Model
+    model = sarimax.SARIMAX(tss['Sales'],trend='n',order=(1,1,1),seasonal_order=(1,1,1,12))
+    results = model.fit(disp=-1)
+
+    # Forecasting
+    y_pred = pd.DataFrame(results.forecast(len(tss_valid)))
+    y_pred.index=tss_valid.index
+
+    # Evaluation metric-rmse
+    rmse = math.pow(mean_squared_error(tss_valid.values,y_pred.values),0.5)
+
+    return y_pred,rmse
+
 
-    "write your solution here"
-