Assessing Climate data to understand¶

Climate change is impacting the way people live around the world

The DATA DESCRIPTION AND CITATION HERE 🛎️

Study Area: New Delhi¶

New Delhi is the capital of India, and it's also an urban district within the larger city of Delhi.¶

alt text

In [1]:
# Import libraries
import holoviews as hv
import hvplot.pandas
import pandas as pd
In [2]:
NewDelhi_url = ('https://www.ncei.noaa.gov/access/services/data/v1?'
          'dataset=daily-summaries'
          '&dataTypes=PRCP,TAVG,TMAX,TMIN'
          '&stations=IN022021900'
          '&startDate=1901-01-01'
          '&endDate=2025-07-27'
          '&units=standard')
NewDelhi_url
Out[2]:
'https://www.ncei.noaa.gov/access/services/data/v1?dataset=daily-summaries&dataTypes=PRCP,TAVG,TMAX,TMIN&stations=IN022021900&startDate=1901-01-01&endDate=2025-07-27&units=standard'

Downloading and working with NCEI Data¶

Here we have used earthpy to download data from your API URL.

In [ ]:
# Download the climate data
New_delhi_df = pd.read_csv(
    NewDelhi_url,
     index_col='DATE',
     parse_dates=True,
     na_values=['NaN']
)

# Check that the download worked
New_delhi_df.head()
In [ ]:
New_delhi_df = New_delhi_df[['PRCP', 'TAVG','TMAX','TMIN']]
New_delhi_df
Out[ ]:
PRCP TAVG TMAX TMIN
DATE
1901-01-01 0.31 NaN NaN NaN
1901-01-02 0.00 NaN NaN NaN
1901-01-03 0.00 NaN NaN NaN
1901-01-04 0.00 NaN NaN NaN
1901-01-05 0.00 NaN NaN NaN
... ... ... ... ...
2025-07-23 NaN 83.0 91.0 78.0
2025-07-24 NaN 89.0 NaN 77.0
2025-07-25 NaN 91.0 NaN 82.0
2025-07-26 0.00 90.0 98.0 81.0
2025-07-27 NaN 91.0 98.0 84.0

44566 rows × 4 columns

Data Subsetting¶

In [ ]:
# Subset the data 1975 - 2025
ND_1975_2025 = New_delhi_df['1975':'2025']
ND_1975_2025
Out[ ]:
PRCP TAVG TMAX TMIN
DATE
1975-01-01 0.63 52.0 55.0 NaN
1975-01-02 0.02 53.0 63.0 43.0
1975-01-03 0.00 52.0 64.0 45.0
1975-01-04 0.00 54.0 66.0 43.0
1975-01-05 0.00 53.0 68.0 43.0
... ... ... ... ...
2025-07-23 NaN 83.0 91.0 78.0
2025-07-24 NaN 89.0 NaN 77.0
2025-07-25 NaN 91.0 NaN 82.0
2025-07-26 0.00 90.0 98.0 81.0
2025-07-27 NaN 91.0 98.0 84.0

18317 rows × 4 columns

Ploting the precpitation column (PRCP) vs time¶

In [ ]:
ND_1975_2025.plot(
    y='PRCP',
    title='NEW Delhi-Precipitation',
    xlabel='Date ',
    ylabel='Precipitation in (mm)')
Out[ ]:
<Axes: title={'center': 'NEW Delhi-Precipitation'}, xlabel='Date ', ylabel='Precipitation in (mm)'>
No description has been provided for this image

Plotting Average Temperature vs Time

In [ ]:
# Plot the temperature vs time
ND_1975_2025.plot(
    y='TAVG',
    title='NEW Delhi Average Temperature',
    xlabel='Date ',
    ylabel='Temperature in (Degree Farheinhite)'
)
Out[ ]:
<Axes: title={'center': 'NEW Delhi Average Temperature'}, xlabel='Date ', ylabel='Temperature in (Degree Farheinhite)'>
No description has been provided for this image
In [ ]:
# Write a function to convert Fahrenheit to Celsius
def fah_to_cel(fah):
    """Convert temperature to Celcius"""
    return (fah-32)*5/9 # Put your equation in here

ND_1975_2025['Celcius'] = ND_1975_2025['TAVG'].apply(fah_to_cel)
ND_1975_2025

/tmp/ipykernel_1039/3902032077.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  ND_1975_2025['Celcius'] = ND_1975_2025['TAVG'].apply(fah_to_cel)
Out[ ]:
PRCP TAVG TMAX TMIN Celcius
DATE
1975-01-01 0.63 52.0 55.0 NaN 11.111111
1975-01-02 0.02 53.0 63.0 43.0 11.666667
1975-01-03 0.00 52.0 64.0 45.0 11.111111
1975-01-04 0.00 54.0 66.0 43.0 12.222222
1975-01-05 0.00 53.0 68.0 43.0 11.666667
... ... ... ... ... ...
2025-07-23 NaN 83.0 91.0 78.0 28.333333
2025-07-24 NaN 89.0 NaN 77.0 31.666667
2025-07-25 NaN 91.0 NaN 82.0 32.777778
2025-07-26 0.00 90.0 98.0 81.0 32.222222
2025-07-27 NaN 91.0 98.0 84.0 32.777778

18317 rows × 5 columns

In [ ]:
# Write a function to convert Fahrenheit to Celsius
def fah_to_cel(fah):
    """Convert temperature to Celcius"""
    return (fah-32)*5/9 # Put your equation in here

ND_1975_2025['Celcius_TMAX'] = ND_1975_2025['TMAX'].apply(fah_to_cel)
ND_1975_2025

/tmp/ipykernel_1039/1610806823.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  ND_1975_2025['Celcius_TMAX'] = ND_1975_2025['TMAX'].apply(fah_to_cel)
Out[ ]:
PRCP TAVG TMAX TMIN Celcius Celcius_TMAX
DATE
1975-01-01 0.63 52.0 55.0 NaN 11.111111 12.777778
1975-01-02 0.02 53.0 63.0 43.0 11.666667 17.222222
1975-01-03 0.00 52.0 64.0 45.0 11.111111 17.777778
1975-01-04 0.00 54.0 66.0 43.0 12.222222 18.888889
1975-01-05 0.00 53.0 68.0 43.0 11.666667 20.000000
... ... ... ... ... ... ...
2025-07-23 NaN 83.0 91.0 78.0 28.333333 32.777778
2025-07-24 NaN 89.0 NaN 77.0 31.666667 NaN
2025-07-25 NaN 91.0 NaN 82.0 32.777778 NaN
2025-07-26 0.00 90.0 98.0 81.0 32.222222 36.666667
2025-07-27 NaN 91.0 98.0 84.0 32.777778 36.666667

18317 rows × 6 columns

In [ ]:
# Resample the data to look at yearly mean values
ND_1975_2025_mean = ND_1975_2025.resample('Y-Jul').mean()
ND_1975_2025_mean

/tmp/ipykernel_1039/1138109287.py:2: FutureWarning: 'Y-Jul' is deprecated and will be removed in a future version, please use 'YE-JUL' instead.
  ND_1975_2025_mean = ND_1975_2025.resample('Y-Jul').mean()
Out[ ]:
PRCP TAVG TMAX TMIN Celcius Celcius_TMAX
DATE
1975-07-31 0.031364 78.213270 87.983784 66.424419 25.674039 31.102102
1976-07-31 NaN 75.941667 86.789474 65.169960 24.412037 30.438596
1977-07-31 0.075771 76.384615 87.232198 67.097701 24.658120 30.684555
1978-07-31 0.068562 76.860274 87.099099 66.226766 24.922374 30.610611
1979-07-31 0.112605 76.413699 87.763533 66.515152 24.674277 30.979740
1980-07-31 0.061532 77.773224 89.571831 66.175325 25.429569 31.984351
1981-07-31 0.066817 77.227397 88.274238 65.944954 25.126332 31.263466
1982-07-31 0.079267 75.597260 86.843575 64.944984 24.220700 30.468653
1983-07-31 0.043962 75.591781 86.807910 64.770898 24.217656 30.448839
1984-07-31 0.051622 76.480769 88.347458 64.974359 24.711538 31.304143
1985-07-31 0.105504 76.778082 89.487395 65.520124 24.876712 31.937442
1986-07-31 0.055165 75.887671 87.169444 64.790850 24.382040 30.649691
1987-07-31 0.036322 77.335165 89.305556 65.902821 25.186203 31.836420
1988-07-31 0.053166 78.084699 90.569405 66.459732 25.602611 32.538558
1989-07-31 0.089492 76.033708 88.658385 64.842657 24.463171 31.476881
1990-07-31 0.051074 76.194521 87.842262 65.731707 24.552511 31.023479
1991-07-31 0.068505 76.985380 90.146429 67.775785 24.991878 32.303571
1992-07-31 0.105891 75.465839 87.228782 64.357798 24.147688 30.682657
1993-07-31 0.065094 76.264957 88.289231 64.283276 24.591643 31.271795
1994-07-31 0.133053 76.679558 88.438235 65.669967 24.821977 31.354575
1995-07-31 0.050982 76.779006 88.492754 65.423676 24.877225 31.384863
1996-07-31 0.140979 76.450820 88.091691 65.345161 24.694900 31.162050
1997-07-31 0.064636 74.616438 86.890805 62.874194 23.675799 30.494891
1998-07-31 0.075732 75.526027 86.696793 65.515358 24.181126 30.387107
1999-07-31 0.173099 76.588889 88.157100 66.423729 24.771605 31.198389
2000-07-31 0.117425 76.314208 88.356083 65.564014 24.619004 31.308935
2001-07-31 0.216301 76.134615 88.365439 64.919463 24.519231 31.314133
2002-07-31 0.288222 78.013699 90.787966 66.882911 25.563166 32.659981
2003-07-31 0.133197 76.230769 88.123944 65.522876 24.572650 31.179969
2004-07-31 0.039466 76.833333 88.669492 66.058632 24.907407 31.483051
2005-07-31 0.078266 76.668493 88.438889 65.624615 24.815830 31.354938
2006-07-31 0.387321 77.194521 90.087079 64.882175 25.108067 32.270599
2007-07-31 0.262676 77.109890 89.081461 66.589172 25.061050 31.711923
2008-07-31 0.265217 75.807692 88.498615 64.715686 24.337607 31.388119
2009-07-31 0.262754 77.887671 90.814085 66.996914 25.493151 32.674491
2010-07-31 0.307468 78.155125 90.468750 67.394984 25.641736 32.482639
2011-07-31 0.344157 76.000000 88.014085 65.839117 24.444444 31.118936
2012-07-31 0.219556 77.363388 90.200549 66.557994 25.201882 32.333639
2013-07-31 0.395960 76.312329 88.949721 65.288344 24.617960 31.638734
2014-07-31 0.229000 76.605479 88.867403 65.573574 24.780822 31.593002
2015-07-31 0.239398 76.915068 89.275568 65.740625 24.952816 31.819760
2016-07-31 0.281053 79.704110 90.569288 67.660131 26.502283 32.538494
2017-07-31 0.253368 79.680441 91.095506 66.990536 26.489134 32.830836
2018-07-31 0.206949 78.227397 91.599119 66.394984 25.681887 33.110622
2019-07-31 0.245085 77.814404 89.336842 64.219048 25.452447 31.853801
2020-07-31 0.291262 76.707650 88.186603 65.486068 24.837583 31.214779
2021-07-31 0.420805 77.828729 90.965174 63.768997 25.460405 32.758430
2022-07-31 0.359885 77.805479 92.587786 66.148607 25.447489 33.659881
2023-07-31 0.350476 76.164384 89.472727 64.252226 24.535769 31.929293
2024-07-31 0.324384 77.234463 90.815686 65.532915 25.130257 32.675381
2025-07-31 0.329070 77.312676 90.790393 66.296774 25.173709 32.661329

Plot resampled data 📈

In [ ]:
# Plot mean annual temperature values
# using hvplot
import hvplot.pandas
(ND_1975_2025.hvplot(
    y='Celcius',
    title='NEW Delhi Mean Annual Temperature',
    xlabel='DATE',
    ylabel='Temperature in (C)')
+
ND_1975_2025_mean.hvplot(
    y='Celcius',
    title='New Delhi Mean Annual Temperature',
    xlabel='DATE',
    ylabel='Temperature in (C)',shared_axes=False)).cols(1)
Out[ ]:
In [ ]:
# Plot Annual Max temperature values
# using hvplot
import hvplot.pandas
(ND_1975_2025.hvplot(
    y='Celcius_TMAX',
    title='New Delhi Annual Maximum Temperature',
    xlabel='DATE',
    ylabel='Temperature in (C)')
+
ND_1975_2025_mean.hvplot(
    y='Celcius_TMAX',
    title='New Delhi Annual Maximum Temperature',
    xlabel='DATE',
    ylabel='Temperature in (C)',shared_axes=False)).cols(1)
Out[ ]:

Storing variables¶

In [ ]:
%store ND_1975_2025 ND_1975_2025_mean NewDelhi_url New_delhi_df

Stored 'ND_1975_2025' (DataFrame)
Stored 'ND_1975_2025_mean' (DataFrame)
Stored 'NewDelhi_url' (str)
Stored 'New_delhi_df' (DataFrame)
In [ ]:
%%capture
%%bash
#Coverting to HTML
jupyter nbconvert climate-98-download.ipynb --to html

Finally, be sure to Restart and Run all to make sure your notebook works all the way through!