04 01 Preparing data - HannaAA17/Data-Scientist-With-Python-datacamp GitHub Wiki

# Import pandas
import pandas as pd

# Create the list of file names: filenames
filenames = ['Gold.csv', 'Silver.csv', 'Bronze.csv']

# Create the list of three DataFrames: dataframes
dataframes = []
for filename in filenames:
    dataframes.append(pd.read_csv(filename))

# Print top 5 rows of 1st DataFrame in dataframes
print(dataframes[0].head())

# Import pandas
import pandas as pd

# Make a copy of gold: medals
medals = gold.copy()

# Create list of new column labels: new_labels
new_labels = ['NOC', 'Country', 'Gold']

# Rename the columns of medals using new_labels
medals.columns = new_labels

# Add columns 'Silver' & 'Bronze' to medals
medals['Silver'] = silver['Total']
medals['Bronze'] = bronze['Total']

# Print the head of medals
print(medals.head())

# Import pandas
import pandas as pd

# Read 'monthly_max_temp.csv' into a DataFrame: weather1
weather1 = pd.read_csv('monthly_max_temp.csv',index_col='Month')

# Print the head of weather1
print(weather1.head())

# Sort the index of weather1 in alphabetical order: weather2
weather2 = weather1.sort_index()

# Print the head of weather2
print(weather2.head())

# Sort the index of weather1 in reverse alphabetical order: weather3
weather3 = weather1.sort_index(ascending=False)

# Print the head of weather3
print(weather3.head())

# Sort weather1 numerically using the values of 'Max TemperatureF': weather4
weather4 = weather1.sort_values('Max TemperatureF')

# Print the head of weather4
print(weather4.head())

# Import pandas
import pandas as pd

# Reindex weather1 using the list year: weather2
weather2 = weather1.reindex(year)

# Print weather2
print(weather2)

# Reindex weather1 using the list year with forward-fill: weather3
weather3 = weather1.reindex(year).ffill()

# Print weather3
print(weather3)

# Import pandas
import pandas as pd

# Reindex names_1981 with index of names_1881: common_names
common_names = names_1981.reindex(names_1881.index)

# Print shape of common_names
print(common_names.shape)

# Drop rows with null counts: common_names
common_names = common_names.dropna()

# Print shape of new common_names
print(common_names.shape)

# Extract selected columns from weather as new DataFrame: temps_f
temps_f = weather[['Min TemperatureF','Mean TemperatureF','Max TemperatureF']]

# Convert temps_f to celsius: temps_c
temps_c = (temps_f - 32) * 5/9

# Rename 'F' in column names with 'C': temps_c.columns
temps_c.columns = temps_c.columns.str.replace('F','C')

# Print first 5 rows of temps_c
print(temps_c.head())

import pandas as pd

# Read 'GDP.csv' into a DataFrame: gdp
gdp = pd.read_csv('GDP.csv',parse_dates=True,index_col='DATE')

# Slice all the gdp data from 2008 onward: post2008
post2008 = gdp.loc['2008-01-01':]

# Print the last 8 rows of post2008
print(post2008.tail(8))

# Resample post2008 by year, keeping last(): yearly
yearly = post2008.resample('A').last()

# Print yearly
print(yearly)

# Compute percentage growth of yearly: yearly['growth']
yearly['growth'] = yearly.pct_change()*100

# Print yearly again
print(yearly)

<script.py> output:
                  VALUE
    DATE               
    2014-07-01  17569.4
    2014-10-01  17692.2
    2015-01-01  17783.6
    2015-04-01  17998.3
    2015-07-01  18141.9
    2015-10-01  18222.8
    2016-01-01  18281.6
    2016-04-01  18436.5
                  VALUE
    DATE               
    2008-12-31  14549.9
    2009-12-31  14566.5
    2010-12-31  15230.2
    2011-12-31  15785.3
    2012-12-31  16297.3
    2013-12-31  16999.9
    2014-12-31  17692.2
    2015-12-31  18222.8
    2016-12-31  18436.5
                  VALUE    growth
    DATE                         
    2008-12-31  14549.9       NaN
    2009-12-31  14566.5  0.114090
    2010-12-31  15230.2  4.556345
    2011-12-31  15785.3  3.644732
    2012-12-31  16297.3  3.243524
    2013-12-31  16999.9  4.311144
    2014-12-31  17692.2  4.072377
    2015-12-31  18222.8  2.999062
    2016-12-31  18436.5  1.172707

# Import pandas
import pandas as pd

# Read 'sp500.csv' into a DataFrame: sp500
sp500 = pd.read_csv('sp500.csv', parse_dates=True, index_col='Date')

# Read 'exchange.csv' into a DataFrame: exchange
exchange =pd.read_csv('exchange.csv', parse_dates=True, index_col='Date')

# Subset 'Open' & 'Close' columns from sp500: dollars
dollars = sp500[['Open','Close']]

# Print the head of dollars
print(dollars.head())

# Convert dollars to pounds: pounds
pounds = dollars.multiply(exchange['GBP/USD'],axis='rows')

# Print the head of pounds
print(pounds.head())

In [3]: dollars.head()
Out[3]: 
                   Open        Close
Date                                
2015-01-02  2058.899902  2058.199951
2015-01-05  2054.439941  2020.579956
2015-01-06  2022.150024  2002.609985
2015-01-07  2005.550049  2025.900024
2015-01-08  2030.609985  2062.139893

In [4]: exchange.head()
Out[4]: 
            GBP/USD
Date               
2015-01-02  0.65101
2015-01-05  0.65644
2015-01-06  0.65896
2015-01-07  0.66344
2015-01-08  0.66151

In [5]: pounds.head()
Out[5]: 
                   Open        Close
Date                                
2015-01-02  1340.364425  1339.908750
2015-01-05  1348.616555  1326.389506
2015-01-06  1332.515980  1319.639876
2015-01-07  1330.562125  1344.063112
2015-01-08  1343.268811  1364.126161