如何将训练和测试数据加在一起以同时绘制两者？

Question

我有类似这样的数据。

Year    Quarter Quantity    Price
2000    1   23  142
2000    2   23  144
2000    3   23  147
2000    4   23  151
2001    1   22  160
2001    2   22  183
2001    3   22  186
2001    4   22  186
2002    1   21  212
2002    2   19  232
2002    3   19  223
2002    4   19  224
2003    1   19  231
2003    2   19  228
2003    3   19  238
2003    4   19  238
2004    1   19  234
2004    2   19  231

我将其分为测试数据和培训数据，如下所示。一切正常，直到print(my_submission.head())。最后，我试图将测试结果附加到训练数据上，以便可以将所有内容绘制在图表中，就像这样。

如何创建类似的图表？这是我的所有代码。

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import statsmodels.api as sm
import seaborn as sns
import sklearn
from statsmodels.formula.api import ols
from seaborn import heatmap


df = pd.read_csv('C:\\my_path_here\\insurance.csv')
df.head(10)
df.tail(10)


# Check null value
print(df.isnull().sum())

# Check zero value
print((df == 0).astype(int).sum(axis=0))

# Check for any duplicates
df.drop_duplicates()



data_model = ols("Quantity ~ Price", data=df).fit()
print(data_model.summary())


fig = plt.figure(figsize=(12,8))
fig = sm.graphics.plot_partregress_grid(data_model, fig=fig)


fig = plt.figure(figsize=(12, 8))
fig = sm.graphics.plot_ccpr_grid(data_model, fig=fig)



fig = plt.figure(figsize=(12,8))
fig = sm.graphics.plot_regress_exog(data_model, 'Price', fig=fig)



df1 = df.groupby(['Year']).agg({'Quantity':'sum','Price':'sum'}).reset_index()
# another way to do the aggregation to setup dataset for the pivot
#df1 = df.groupby(['Year'])["Quantity", "Price"].apply(lambda x : x.astype(int).sum())


X = df[['Year', 'Quantity', 'Price']]
import matplotlib.pyplot as plt
corr = X.corr()


sns.heatmap(corr, xticklabels=corr.columns,yticklabels=corr.columns, annot=True)


df2 = df.pivot('Year', 'Quarter', 'Price')
f, ax = plt.subplots(figsize=(5, 15))
sns.heatmap(df2, linewidths=.5, ax=ax, annot=True, fmt='.1f')


rev_df_revenue = df.pivot('Quantity',values='Price')
heatmap(rev_df_revenue, annot=True, fmt=".2f")
plt.title('Heatmap of Price')


# everythign looks OK up to this point...
# Split into training set and test set
train, test = sklearn.model_selection.train_test_split(df, train_size = 0.8)

train.shape
test.shape
print(train.dtypes)
print(test.dtypes)



# Start features engineering process
# set X as the independent variable and y as the dependent variable
# we will drop 'trip_duration' from the training dataset; 
# other factors can influence our ability to make predictions
y = train['Price']
train.drop(['Price'], axis=1, inplace=True)
X = train
X.shape, y.shape


# start to test
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
X_train.shape, y_train.shape, X_test.shape, y_test.shape


# start to validate
X_train, X_valid, y_train, y_valid = train_test_split(X_train, y_train, random_state=42)
X_train.shape, y_train.shape, X_valid.shape, y_valid.shape


from sklearn.ensemble import RandomForestRegressor
m1 = RandomForestRegressor(n_estimators=19, min_samples_split=2, min_samples_leaf=4, max_features='auto', max_depth=80, bootstrap=True)
m1.fit(X_train, y_train)
m1.score(X_valid, y_valid)


test_columns = X_train.columns
predictions = m1.predict(test[test_columns])


my_submission = pd.DataFrame({'Quantity': test.Quantity, 'Price': predictions})
print(my_submission.head())


train.Price.plot(figsize=(15,8), title= 'Price', fontsize=14)
test.Price.plot(figsize=(15,8), title= 'Price', fontsize=14)
plt.show()