Pandas
Getting started
import pandas as pd
Docu
nice cheat sheets can be found here
- https://www.datacamp.com/cheat-sheet/pandas-cheat-sheet-for-data-science-in-python
- https://www.datacamp.com/cheat-sheet/pandas-cheat-sheet-data-wrangling-in-python
Create DF
import pandas as pd
# empty
df = pd.DataFrame()
# from 1 dim list
df = pd.DataFrame(data={"Column Name": lst})
# from N dim list, and set name of columns
df = pd.DataFrame(
data=lst, columns=("num_songs_played", "pct_all_played", "pct_80pct_played")
)
# from multiple lists
data = zip(
l_days,
l_2016,
l_2017,
l_2018,
l_2019,
l_2020,
strict=True,
)
...
from csv
see [1]
df = pd.read_csv("data.tsv", sep="\t")
# only selected columns and parse date
df = pd.read_csv(
"data.tsv",
sep="\t",
decimal=",",
usecols=[
"Date",
"Deaths_New",
], # only load these columns
parse_dates=[
"Date",
], # convert to date object if format is yyyy-mm-dd pr dd.mm.yyyy
index_col="Date", # choose this column as index
na_values=["<4"], # values to treat as NA
)
df = df.rename(columns={"Deaths_New": "Deaths_Covid"})
# convert data upon loading
# read only first 10 chars from 2021-04-29T12:15:00+02:00 -> 2021-04-29
pd_date_converter = lambda x: (x[0:10]) # noqa: E731
df = pd.read_csv(
"data.tsv",
sep=",",
converters={"Datum": pd_date_converter},
parse_dates=[
"Datum", # # convert to date object if format is yyyy-mm-dd
],
)
# convert datetime to date after loading
for c in ("Buchungstag", "Valutadatum"):
df2[c] = pd.to_datetime(df2[c], format="%d.%m.%Y").dt.date
from list[str] via read_csv
from io import StringIO
csv_string_io = StringIO("\n".join(lines))
df = pd.read_csv(
csv_string_io,
sep=";",
)
from Excel
see [2]
import openpyxl # pip install openpyxl
df = pd.read_excel("file.xlsx", sheet_name="Sheet1", engine="openpyxl")
df = pd.read_excel(
"file.xlsx",
skiprows=4,
usecols=[
"ArbPlatz",
"BezArt",
],
)
from dict
see [3]
df = pd.DataFrame.from_dict(d, orient="index", columns=["Col1", Col2])
flatten dict in list of dict
# l1 is list of dict, each dict has a sub-dict called metadata
l2 = []
for item in l1:
flat = item.copy()
meta = item.pop("metadata")
flat.update(meta)
l2.append(flat)
del l1
df = pd.DataFrame.from_dict(l2)
from array/record/list
see [4]
data = [ {"id":1, "name":"asdf"}, {"id":2, "name":"qwertz"}, ]
df = pd.DataFrame.from_records(data)
from JSON
see [5]
df = pd.read_json("file.json")
from SQLite
import sqlite3 sql = "SELECT * FROM tab WHERE col2 = ? ORDER BY id"; df = pd.read_sql_query(sql, con, params=(MY_FILTER_VALUE,))
Export Data
to csv
df.to_csv(
"data.tsv",
sep="\t",
lineterminator="\n",
)
# selected columns only
df[ ["Col1", "Col2"] ].to_csv(
"data.tsv",
sep="\t",
lineterminator="\n",
)
to Excel
see [6]
df.to_excel("data.xlsx", index=False)
Export 2 df as sheets in 1 file
with pd.ExcelWriter(path=file_in.with_suffix(".xlsx")) as writer:
df1.to_excel(writer, sheet_name='Sheet_name_1')
df2.to_excel(writer, sheet_name='Sheet_name_2')
writer.close()
to HTML
see [7]
df.to_html(
"out.html", index=False, render_links=False, escape=False, justify="center"
)
# html encoding of column name only
df["name"] = df["name"].str.encode("ascii", "xmlcharrefreplace").str.decode("utf-8")
# add link to name
df["name"] = "<a href='" + df["url"] + "' target='_blank' >" + df["name"] + "</a>"
# export to html
df[ ["name", "due", "overdue", "priority", "overdue priority"] ].to_html(
"out.html", index=False, render_links=False, escape=False, justify="center"
)
to JSON
json_data = df.values.tolist()
with Path(pathStatsExport / "ts_types_month.json").open(
"w", encoding="UTF-8"
) as fh:
json.dump(
json_data,
fp=fh,
ensure_ascii=False,
sort_keys=False,
indent=2,
)
Modification
Add Row
add row from list to end
idx = df.index[-1] + 1 list_of_values = (...) df.loc[idx] = list_of_values
add dummy row for missing 1.1.2020 and reindex
df.loc[-1] = "2020-01-01", 0 df.index = df.index + 1 # shifting index df = df.sort_index() # sorting by index
Replace na Values
df = df.dropna() # only in certain columns df = df.dropna(subset=["power", "heart_rate", "cadence"]) df = df[df["value"].notna()]
Interpolate missing values
# interpolate missing data, e.g. after df.groupby([pd.Grouper(key="time", freq="1min")]) df["kWh_total_in"] = df["kWh_total_in"].interpolate(method="linear")
Calc Diff / Delta of rows
df["delta_prev"] = df["kWh"].diff() df["delta_next"] = df["kWh"].shift(-1) - df["kWh"]
Read-out Data
Columns
df2 = df [ [ "col1", "col2" ] ]
Rows
for index, row in df.iterrows():
Aggregation
Sum Column or Row
# sum of 1 column sum_cases = df["Cases"].sum() # sum per column df_sums = df.sum(axis="columns") # sum per row / index df_sums = df.sum(axis="index")
Filtering
Basics
# new notation
df = df.query("power >= 80 & cadence >= 40")
# old notation
df = df[ df["power"] >= 80 ]
df = df[ (df["power"] >= 80) & (df["cadence"] >= 40) ]
# ~ inverts
# list of multiple values
df = df[ ~df["col1"].isin(("A", "B", "C")) ]
filter on index
df = df[df.index >= start_yearweek]
df = df.drop("Summe")
Filtering Dates
# filter a date column via year
df = df[df["Date"].dt.year == 2020]
# filter a date via str
df = df[df["Date"] == "2021-11-13"]
# filter on date via dt
df = df[
df["RECEIVE_DATE"].dt.date # convert pandas datetime64[ns] to date
>= (dt.date.today() - dt.timedelta(days=30))
]
Drop Duplicate Rows
df = df.drop_duplicates()
Date Handling
Dates
Convert Column to Date
df["Date"] = pd.to_datetime(df["Date]) df["Date"] = pd.to_datetime(df["Date"], format="%Y-%m-%d") df["Year"] = df["Date"].dt.year
Week num to Date
# V2
def get_date_of_week_start(year, week_number) -> dt.date:
date = dt.date.fromisocalendar(int(year), int(week_number), 1)
return date
df["date"] = df.apply(
lambda row: get_date_of_week_start(row["year"], row["week"]),
axis=1,
)
# V1
# split "week/year" to date
# 51/2021 -> date of sunday
def convert2date(s: str) -> dt.date:
week, year = s.split("/")
date = dt.date.fromisocalendar(int(year), int(week), 1)
return date
df["dt"] = df["Kalenderwoche"].apply(lambda x: convert2date(x))
Date to Start of Week
df["week_start"] = df["date"].dt.to_period("W").apply(lambda r: r.start_time)
DateTime
DateTime: remove miliseconds
df["DateTime"] = df["DateTime"].dt.ceil(freq="s")
Remove timezone offset info
# V1: proper aproach using tz_convert(None)
df[col] = pd.to_datetime(df[col], format="%Y-%m-%dT%H:%M:%S%z")
df[col] = df[col].dt.tz_convert(None)
# if it throws:
# AttributeError: Can only use .dt accessor with datetimelike values. Did you mean: 'at'?
# see V2
# V2: simple removing the timezone offset
# Remove the timezone information by replacing the "+01:00", "+02:00", "-02:00",
# etc. with an empty string
df[col] = df[col].str.replace(r"[+\-]\d{2}:\d{2}.*$", "", regex=True)
# Parse the datetime column without timezone information
df[col] = pd.to_datetime(df[col], format="%Y-%m-%dT%H:%M:%S")
# note: now without the timezone %z info: format="%Y-%m-%dT%H:%M:%S%z"
TimeZone conversion
# convert UTC to local time
df["DateTime"] = (
df["DateTime"]
.dt.tz_localize("utc")
.dt.tz_convert(tz="Europe/Berlin")
# drop timezone info, since Excel can not handle it
.dt.tz_localize(None)
)
TimeStamps
Convert Timestamp to Datetime and use as Index
df["datetime"] = pd.to_datetime( # convert to datetime
df["start_ts"],
unit="s", # timestamp is in seconds
utc=True, # timestamp is in UTC
).dt.tz_convert( # convert to local TZ
"Europe/Berlin"
)
df = df.set_index("datetime")
Convert Datetime to Timestamp
df["timestamp"] = df["datetime"].values.astype(np.int64) // 10**9 # or df["timestamp"] = df["datetime"].astype(int) // 10**9 # // is integer division
Timestamp: substract first
# calc elapsed time df["seconds"] = df["timestamp"] - df["timestamp"].iloc[0]
String Modifications
Replace
df["name"] = df["name"].str.strip() # trim whitespaces df["time"] = df["time"].str.replace(r"\..*$", "Z", regex=True)
# remove word "Probable"
df["col"] = df["col"].replace(
to_replace=r"^Probable ", value="", regex=True
)
df["Text"] = df["Text"].str.replace(
r"^Menke, *Torben *",
"Torben Menke",
regex=True,
)
split string
df [ [ "week", "year" ] ] = df["Kalenderwoche"].str.split("/", expand=True)
string <-> number
string to float: 1.234,56 -> 1234.56
df["Euro"] = (
df["Euro"]
.str.replace(".", "")
.str.replace(",", ".")
.astype(float)
)
convert int to str adding leading zeros
df["Sterbewoche"].astype(str).str.zfill(2)
capitalization
df["Wer"] = df["Wer"].apply(lambda x: string.capwords(x))
trim spaces
df["Wer"] = df["Wer"].str.strip()
count word per row and check if more than one
str.count()
df["cnt_Buchungstext"] = df["Text"].str.count("word")
df_search = df[df["cnt_Buchungstext"] != 1]
if len(df_search) > 0:
print(df_search)
del df_search
df = df.drop(columns=["cnt_Buchungstext"])
Overwrite Data
# overwrite values > 123 by 123
df["col"] = df["col"].clip(upper=123)
# negative -> 0
df[df < 0] = 0
# overwrite column data of last 3 weeks by None
df["DateAsDate"] = pd.to_datetime(df["Date"], format="%Y-%m-%d")
date_3w = dt.date.today() - dt.timedelta(weeks=3)
df.loc[df["DateAsDate"].dt.date >= date_3w, "MyColumn"] = None
# rolling takes NAN values into account, so I need to overwrite them as well
df3["Deaths_Covid_roll"] = np.where(
df3["Deaths_Covid"].isnull(), np.nan, df3["Deaths_Covid_roll"]
df.loc[(df["Kat2"] == "") & (df["IBAN"] == "DE02100100100152517108"), "Kat2"] = "Bahn"
df.loc[(df["Kat1"] == "") & (df["Kat2"] == "Bahn"), "Kat1"] = "Mobilität"
# assigning multiple values
df.loc[
(df["Kat1"] == "") & (df["IBAN"] == "DE02100100100152517108"),
["Kat1", "Kat2", "Kat3"],
] = ["Mobilität], "Reisen", "Bahn"]
# str endswith
df.loc[
(df["RespTime"] == 0.0)
& (df["Text"].str.endswith("(read timeout=30)")),
"RespTime",
] = 30.0
Sorting / order by
# sort by column df = df.sort_values(by=['betten_belegt'], ascending=False) df = df.sort_values(by=["Buchungstag", "Text"], ignore_index=True)
Top10
df_top_ten = (
df.sort_values(by="count", ascending=False)
.head(10)
)
Group By / Top10
df2 = (
df[ [ "name", "amount" ] ]
.groupby("name")
.agg(amountSum=("amount", "sum"), count=("name", "count"))
.sort_values(by=["amountSum", "count"], ascending=False)
)
print(df2.head(10)) # top10
# resort by count
print(df2.sort_values(by="count", ascending=False).head(10))
Group by Type and Date
# group by hour
# truncate min and sec data
df["hour"] = pd.to_datetime(df["time"]).dt.floor("H")
# sum per hour
df2 = df[ ["hour", "amount"] ].groupby("hour").agg(amountSum=("amount", "sum"))
df2.plot()
plt.show()
# Datetime Index Grouping
df = df.groupby(pd.Grouper(freq="5min", offset="00h00min")).max()
# Group by type and date of month start
df_month = df.groupby(["type", pd.Grouper(key="date", freq="MS")]).agg(
{"id": "count", "minutes": "sum"}
)
# generate index of the desired month-freq:
idx = pd.date_range(
start=df["date"].min().replace(day=1),
end=df["date"].max().replace(day=1),
freq="MS", # MS = Month Start
)
# add missing months
df_month = df_month.reindex(
pd.MultiIndex.from_product(
[df_month.index.get_level_values("type"), idx],
names=["type", "date"],
)
)
# fill missing by 0 and convert count back to type int
df_month = df_month.fillna(0).astype({"count": int})
Group Datetime by Time of Day only
df["Time"] = df["Date"].dt.round("5min").dt.time
df_grouped = df [ ["RespTime", "Time" ] ].groupby("Time").mean()
Group and calculate min,avg,max
df_grouped = (
df[ ["Time", "RespTime"] ]
.groupby("Time")
.agg(
max=pd.NamedAgg(column="RespTime", aggfunc="max"),
avg=pd.NamedAgg(column="RespTime", aggfunc="mean"),
min=pd.NamedAgg(column="RespTime", aggfunc="min"),
)
)
Column Handling
Renaming
df = df.rename(
columns = {"invasiv_beatmet": "beatmet",},
errors="raise",
)
rename column headers by extracting some int values from a string
l2 = []
for col in df.columns:
year = int(col[0:4])
week = int(col[5:7])
l2.append(year * 100 + week)
df.columns = l2
Dropping
drop columns
df = df.drop(columns=["Sterbejahr", "Sterbewoche"])
Change Column Order
df = df.reindex(
[
"Wann",
"Art",
"Wer",
],
axis="columns",
)
# move certain columns to front, leaving the remaining unchanged
first_colmns = ("description", "isin", "side", "quantity", "Price", "amount")
i = 0
for col in first_colmns:
df.insert(i, col, df.pop(col))
i += 1
del i
Index Handling
select column as index
df = df.set_index("Date")
move date from index back to column
df = df.reset_index()
rename index
df.index.name = "Date"
reset index to start at 0
df2 = df1[1 * 365 : 2 * 365].reset_index(drop=True)
extract cell based on Index
col1_first = df2["col1"].iloc[0] de_sum = df["col"].loc["Summe"]
text indexes
df = df.set_index("Altersgruppe")
datetime indexes
# select "Date" column as index
df = df.set_index(["Date"])
# convert index to datetime
df.index = pd.to_datetime(df.index)
# add missing dates
df = df.reindex(
pd.date_range(df.index.min(), df.index.max(), freq="D"), fill_value=0
)
df.index.name = "date"
# remove timezone offset (for Excel can not handle this)
df.index = df.index.tz_localize(None)
date_last = df.index[-1])
# reindex and fill missing with 0
date_last = pd.to_datetime(df.index[-1]).date()
idx = pd.date_range('2020-01-01', date_last))
df = df.reindex(idx, fill_value=0)
# add missing dates
df = df.asfreq('D', fill_value=0)
df = df.asfreq(freq="5M")
df = df.sort_index() # needed?
# drop values of column for last 3 weeks
date_3w = dt.date.today() - dt.timedelta(weeks=3)
df.loc[df.index.date >= date_3w, "Cases"] = None
# or
df.loc[df.index.date < pd.to_datetime("2020-03-01"), "Value"] = None
filter on date index
# drop data prior to 2020 df = df.loc['2020-01-01':] # alternative: df = df[df.index >= "2021-01-10"]
Pivot, UnPivot/Melt
TODO: Pivot
melt/unpivot wide table to long table format
df2 = pd.melt(df, id_vars="Date", value_vars=df.columns[1:]) #
df2 = df2.rename(columns={"variable": "Machine", "value": "Status"})
# not working, using melt instead
# df3 = pd.wide_to_long(df, stubnames="Date", i=df.columns[1:], j="Status")
Merge/Concat and Append DFs
Merge/Concat
df_sum = pd.DataFrame()
df_sum = pd.concat(
[df_sum, df],
ignore_index=True,
)
Append
# join series of 2 df
df_covid_2020 = pd.DataFrame()
df_covid_2020['Deaths_Covid_2020'] = df1['Deaths_Covid_2020'].append(
df2['Deaths_Covid_2020'], ignore_index=True)
df = pd.concat([df, df2], axis=1) # note: this would require all index of df in df2 present: # df[machine] = df2[machine]
Rolling Average, mean of columns, min, max
df['2016_roll'] = df['2016'].rolling(window=7, min_periods=1).mean().round(1)
df['2017_roll'] = df['2017'].rolling(window=7, min_periods=1).mean().round(1)
df['2018_roll'] = df['2018'].rolling(window=7, min_periods=1).mean().round(1)
df['2019_roll'] = df['2019'].rolling(window=7, min_periods=1).mean().round(1)
df['2020_roll'] = df['2020'].rolling(window=7, min_periods=1).mean().round(1)
# mean value of 4 columns
df['2016_2019_mean'] = df.iloc[:, [1, 2, 3, 4]
].mean(axis=1) # not column 0 = day
df['2016_2019_mean_roll'] = df['2016_2019_mean'].rolling(
window=7, min_periods=1).mean().round(1)
df['2016_2019_roll_max'] = df.iloc[:, [6, 7, 8, 9]].max(axis=1)
df['2016_2019_roll_min'] = df.iloc[:, [6, 7, 8, 9]].min(axis=1)
Helpers
def pandas_set_date_index(df, date_column: str):
""" use date as index """
df[date_column] = pd.to_datetime(df[date_column], format='%Y-%m-%d')
df = df.set_index([date_column])
return df
def pandas_calc_roll_av(df, column: str, days: int = 7):
""" calc rolling average over column """
df[column + '_roll_av'] = df[column].rolling(
window=days, min_periods=1).mean().round(1)
return df
# custom rounding
def custom_round(x: float, base: int = 5) -> int:
"""Custom rounding."""
# from https://stackoverflow.com/questions/40372030/pandas-round-to-the-nearest-n
return int(base * round(float(x) / base))
df["power_rounded"] = df["power"].apply( lambda x: custom_round(x, base=20) )
Transpose
df = df.transpose()
Leftovers
# when in a function one might get the SettingWithCopyWarning, fix via df = df.copy()
# copy df2['Date'] = df0['Date'] # drop 2 rows from the beginning df = df2.drop([0, 1])
append today using yesterdays value
str_today = dt.datetime.today().strftime("%Y-%m-%d")
ts_today = pd.Timestamp(str_today)
if df.index[-1] != ts_today:
df.loc[ts_today] = df.loc[df.index[-1], "Count"]
Plotting via Matplotlib
see Matplotlib