Last active
June 6, 2020 08:46
-
-
Save MarcinMoskala/f634eb20e6907845ff68da13260d29f3 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
def add_day_month_year(df): | |
dates = df["Date"].map(lambda x: x[:10]) | |
df["day_of_month"] = dates.map(lambda x: x.split("/")[1]) | |
df["month"] = dates.map(lambda x: x.split("/")[0]) | |
df["year"] = dates.map(lambda x: x.split("/")[2]) | |
df["date"] = dates | |
return df | |
from pandas import read_csv | |
crimes_df = read_csv("CrimeData.csv") | |
crimes_df = add_day_month_year(crimes_df) | |
crimes_df = crimes_df[crimes_df.year <= "2019"] | |
crimes_count_df = crimes_df \ | |
.groupby(["year", "month"]) \ | |
.size() \ | |
.to_frame("crimes") \ | |
.reset_index() | |
from calendar import monthrange | |
crimes_count_df["Days in month"] = crimes_count_df.apply(lambda row: monthrange(int(row.year), int(row.month))[1], axis=1) | |
crimes_count_df["Average crimes"] = crimes_count_df.apply(lambda row: row["crimes"] / row["Days in month"], axis=1) | |
df = crimes_count_df \ | |
.groupby(["month"])["Average crimes"] \ | |
.mean() \ | |
.reset_index() | |
print(crimes_count_df.to_string()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment