kristoferssolo/School
1
0
Fork 0
mirror of https://github.com/kristoferssolo/School.git synced 2025-10-21 20:10:38 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

fixed duplicates drop

Browse Source
This commit is contained in:
Krisotfers-Solo 2022-02-22 21:56:58 +02:00
parent fa0455863e
commit 7c17cc2ba0
4 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
february/task_180222/output/graphs/cenu_grafiki.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 243 KiB

After

Width:  |  Height:  |  Size: 254 KiB

BIN
february/task_180222/output/graphs/korelacija.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 15 KiB

After

Width:  |  Height:  |  Size: 15 KiB

BIN
february/task_180222/output/pdf/secinajumi.pdf
View File

Binary file not shown.

5
february/task_180222/pd_pandas_k_f_cagulis.py
View File

@ -75,8 +75,7 @@ def read():
all_df.append(pd.read_excel(file_path)) all_df.append(pd.read_excel(file_path))
df_combined = pd.concat(all_df).reset_index(drop=True) # combine DataFrames df_combined = pd.concat(all_df).reset_index(drop=True) # combine DataFrames
df_combined.sort_values(by=[PRICE, PUB_DATE], inplace=True) # sort DataFrame df_combined.sort_values(by=[PRICE, PUB_DATE], inplace=True) # sort DataFrame
df_combined.drop_duplicates(keep=False, inplace=True) # drop duplicates df_combined.drop_duplicates(keep="first", inplace=True) # drop duplicates
# replaces floor value to intiger # replaces floor value to intiger
for value in df_combined[FLOOR]: for value in df_combined[FLOOR]:
df_combined = df_combined.replace(value, int(float(value[:value.find("/")]))) df_combined = df_combined.replace(value, int(float(value[:value.find("/")])))
@ -96,7 +95,7 @@ def read():
# converts to datetime # converts to datetime
df_combined[PUB_DATE] = pd.to_datetime(df_combined[PUB_DATE], format="%d.%m.%Y").dt.date df_combined[PUB_DATE] = pd.to_datetime(df_combined[PUB_DATE], format="%d.%m.%Y").dt.date
# df_combined.to_excel("output/excel/combined.xlsx", index=False) df_combined.to_excel("output/excel/combined.xlsx", index=False)
return df_combined.sort_values(by=PUB_DATE) return df_combined.sort_values(by=PUB_DATE)