Created
January 15, 2022 17:11
-
-
Save chrisdmell/e2d02f24aaf7849916ebba369c947814 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
f = final_cleaned_df.copy() | |
b1 = f[(f["Bus"] == "a6951a59b64579edcf822ab9ea4c0c83") & (f["Service_Date"] == "15-07-2020 00:00")] | |
b2 = f[(f["Bus"] == "ab479dab4a9e6bc3eaefe77a09f027ed") & (f["Service_Date"] == "15-07-2020 00:00")] | |
recorded_dates_df = pd.concat([b1[["RecordedAt_new"]], b2[["RecordedAt_new"]]], axis = 0).drop_duplicates().sort_values(by = "RecordedAt_new").reset_index().drop(columns = "index") | |
joined_1 = pd.merge(recorded_dates_df, b1, on=["RecordedAt_new"], how='left',suffixes=('_actuals', '_B1')) | |
joined_df = pd.merge(joined_1, b2, on=["RecordedAt_new"], how='left',suffixes=('_B1', '_B2')) | |
joined_df | |
cols_to_keep = ["RecordedAt_new", "Service_Date_B1","Bus_B1","Bus_B2", "average_price_s1_s2_filled_B1", "average_price_s1_s2_filled_B2"] | |
model_df = joined_df[cols_to_keep] | |
model_df_2 = model_df.drop_duplicates() | |
## replace null of service date | |
model_df_2['Service_Date_B1'] = model_df_2['Service_Date_B1'].fillna(model_df_2['Service_Date_B1'].value_counts().idxmax()) | |
model_df_2['Bus_B1'] = model_df_2['Bus_B1'].fillna(model_df_2['Bus_B1'].value_counts().idxmax()) | |
model_df_2['Bus_B1'] = model_df_2['Bus_B1'].fillna(model_df_2['Bus_B1'].value_counts().idxmax()) | |
model_df_2.fillna(0, inplace = True) | |
test_a = model_df_2.sort_values(by = ["RecordedAt_new" ]) | |
test_a = test_a[["Service_Date_B1","average_price_s1_s2_filled_B1" ]] | |
test_a["average_price_B1_new"] = test_a.groupby(["Service_Date_B1" ]).transform(lambda x: x.replace(to_replace=0, method='bfill')) | |
test_f = model_df_2.sort_values(by = ["RecordedAt_new" ]) | |
test_f = test_f[["Service_Date_B1","average_price_s1_s2_filled_B2" ]] | |
test_f["average_price_B2_new"] = test_f.groupby(["Service_Date_B1" ]).transform(lambda x: x.replace(to_replace=0, method='bfill')) | |
model_df_2["average_price_B1_new"] = test_a["average_price_B1_new"] | |
model_df_2["average_price_B2_new"] = test_f["average_price_B2_new"] | |
model_df_3 = model_df_2[model_df_2["average_price_B1_new"] != 0][["average_price_B1_new","average_price_B2_new"] ] | |
from scipy.stats import hmean | |
## get the price change wrt to each bus price | |
model_df_2["price_cng_b1"] = abs(model_df_2.average_price_B1_new - model_df_2.average_price_B2_new)/model_df_2.average_price_B1_new | |
model_df_2["price_cng_b2"] = abs(model_df_2.average_price_B1_new - model_df_2.average_price_B2_new)/model_df_2.average_price_B2_new | |
model_df_2["harm_mean_price_cng"] = scipy.stats.hmean(model_df_2.iloc[:,8:10],axis=1) | |
model_df_2 = model_df_2[model_df_2["average_price_B1_new"] != 0] | |
model_df_2 = model_df_2[model_df_2["average_price_B2_new"] != 0] | |
model_df_2x = model_df_2.copy() | |
hm = scipy.stats.hmean(model_df_2x.iloc[:,8:10],axis=1) | |
display((max(hm) - min(hm))/ min(hm)) | |
print("======================================================================================================") | |
model_df_3 = model_df_2[model_df_2["average_price_B1_new"] != 0][["price_cng_b1","price_cng_b2"] ] | |
model_df_3.plot(); | |
plt.show() | |
# Create linear regression object | |
regr = linear_model.LinearRegression() | |
# Train the model using the training sets | |
# (X,Y) | |
regr.fit(np.array(model_df_2["price_cng_b1"]).reshape(-1,1),np.array(model_df_2["price_cng_b2"]).reshape(-1,1)) | |
# The coefficients | |
print("Coefficients: \n", regr.coef_) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment