Homework - ameo15 dataset¶

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

d = pd.read_excel('/content/Ameo15.xlsx', index_col='ID')

d.head()

d['Designation'].unique()

array(['senior quality engineer', 'assistant manager', 'systems engineer',
       'senior software engineer', 'get', 'system engineer',
       'java software engineer', 'mechanical engineer',
       'electrical engineer', 'project engineer', 'senior php developer',
       'senior systems engineer', 'quality assurance engineer',
       'qa analyst', 'network engineer', 'product development engineer',
       'associate software developer', 'data entry operator',
       'software engineer', 'developer', 'electrical project engineer',
       'programmer analyst', 'systems analyst', 'ase',
       'telecommunication engineer', 'application developer',
       'ios developer', 'executive assistant', 'online marketing manager',
       'documentation specialist', 'associate software engineer',
       'management trainee', 'site manager', 'software developer',
       '.net developer', 'production engineer', 'jr. software engineer',
       'trainee software developer', 'ui developer',
       'assistant system engineer', 'android developer',
       'customer service', 'test engineer', 'java developer', 'engineer',
       'recruitment coordinator', 'technical support engineer',
       'data analyst', 'assistant software engineer', 'faculty',
       'entry level management trainee',
       'customer service representative', 'software test engineer',
       'firmware engineer', 'php developer', 'research associate',
       'research analyst', 'quality engineer', 'programmer',
       'technical support executive', 'business analyst', 'web developer',
       'application engineer', 'project coordinator', 'engineer trainee',
       'sap consultant', 'quality analyst', 'marketing coordinator',
       'system administrator', 'senior engineer',
       'business development managerde', 'network administrator',
       'technical support specialist', 'business development executive',
       'junior software engineer', 'asp.net developer',
       'graduate engineer trainee', 'field engineer',
       'assistant professor', 'trainee software engineer',
       'senior software developer',
       'quality assurance automation engineer', 'design engineer',
       'telecom engineer', 'quality control engineer',
       'hardware engineer', 'hr recruiter', 'sales associate',
       'junior engineer', 'associate engineer', 'maintenance engineer',
       'sales engineer', 'human resources associate',
       'mobile application developer',
       'electronic field service engineer', 'process associate',
       'field service engineer', 'it support specialist',
       'software development engineer', 'business process analyst',
       'operation engineer', 'electrical designer', 'marketing assistant',
       'sales executive', 'admin assistant', 'senior java developer',
       'account executive', 'oracle dba', 'rf engineer',
       'embedded software engineer', 'programmer analyst trainee',
       'technical engineer', 'operations executive', 'trainee engineer',
       'recruiter', 'lecturer', '.net web developer',
       'marketing executive', 'operations assistant', 'associate manager',
       'electrical design engineer', 'systems administrator',
       'client services associate', 'it analyst', 'senior developer',
       'cad designer', 'business technology analyst', 'asst. manager',
       'service engineer', 'executive recruiter', 'planning engineer',
       'associate technical operations', 'web designer',
       'software architect', 'software quality assurance tester',
       'seo trainee', 'process engineer',
       'software quality assurance analyst', 'designer',
       'business systems consultant', 'business development manager',
       'junior research fellow', 'technical recruiter',
       'operations analyst', 'quality assurance test engineer',
       'linux systems administrator', 'software trainee',
       'entry level sales and marketing', 'electrical field engineer',
       'windows systems administrator', 'junior software developer',
       'python developer', 'web application developer',
       'assistant systems engineer', 'javascript developer',
       'operation executive', 'performance engineer', 'technical writer',
       'operations engineer and jetty handling', 'lead engineer',
       'portfolio analyst', 'associate system engineer',
       'mechanical design engineer', 'product engineer',
       'network security engineer', 'operations manager',
       'technical lead', 'operations', 'quality assurance tester',
       'automation engineer', 'data scientist', 'quality associate',
       'manual tester', 'sr. engineer', 'embedded engineer',
       'service and sales engineer', 'telecom support engineer',
       'engineer- customer support', 'cloud engineer', 'branch manager',
       'business analyst consultant', 'technology lead',
       'software trainee engineer', 'dcs engineer', 'junior manager',
       'ux designer', 'clerical', 'hr generalist',
       'database administrator', 'senior design engineer', 'seo',
       'assistant engineer', 'marketing analyst', 'it executive',
       'salesforce developer', 'software tester', 'sql dba',
       'junior engineer product support', 'manager',
       'senior business analyst', 'c# developer',
       'implementation engineer', 'executive hr', 'executive engineer',
       'sharepoint developer', 'system analyst',
       'sales management trainee', 'senior project engineer',
       'it recruiter', 'software engineer analyst',
       'desktop support technician', 'continuous improvement engineer',
       'process advisor', 'etl developer', 'sales and service engineer',
       'project manager', 'training specialist', 'product manager',
       'staffing recruiter', 'assistant programmer', 'quality controller',
       'mis executive', 'game developer', 'digital marketing specialist',
       'principal software engineer', 'software devloper',
       'senior mechanical engineer', 'technical operations analyst',
       'service coordinator', 'testing engineer', 'technical assistant',
       'sap abap consultant', 'seo engineer', 'project assistant',
       'talent acquisition specialist', 'sales account manager',
       'software engineer trainee', 'customer service manager',
       'help desk analyst', 'general manager', 'engineering manager',
       'senior network engineer',
       'field based employee relations manager', 'phone banking officer',
       'support engineer', 'associate test engineer',
       'technology analyst', 'network support engineer',
       'it business analyst', 'junior system analyst',
       'senior .net developer', 'secretary', 'research engineer',
       'quality assurance auditor', 'process executive',
       'lecturer & electrical maintenance', 'office coordinator',
       'hr manager', 'html developer', 'sales support',
       'front end web developer', 'administrative support',
       'territory sales manager', 'project administrator',
       'environmental engineer', 'web designer and seo',
       'information security analyst',
       'field business development associate', 'operational executive',
       'administrative coordinator', 'senior risk consultant',
       'desktop support engineer', 'cad drafter', 'noc engineer',
       'industrial engineer', 'it engineer', 'human resources intern',
       'senior quality assurance engineer', 'clerical assistant',
       'software enginner', 'quality assurance',
       'delivery software engineer', 'graphic designer',
       'sales development manager', 'visiting faculty',
       'business intelligence analyst', 'team lead',
       'operational excellence manager', 'sales & service engineer',
       'web intern', 'full stack developer', 'database developer',
       'sr. database engineer', 'graduate apprentice trainee',
       'software engineer associate', 'technical analyst',
       'executive engg', 'it technician', 'business system analyst',
       'process control engineer', 'technical consultant',
       'business office manager', 'quality control inspector',
       'product design engineer', 'manufacturing engineer',
       'seo executive', 'sap analyst', 'software engineere',
       'financial service consultant', 'co faculty', 'software analyst',
       'desktop support analyst', 'graduate engineer',
       'engineering technician', 'it assistant', 'marketing manager',
       'human resource assistant', 'hr assistant', 'product developer',
       'customer support engineer',
       'quality control inspection technician', 'gis/cad engineer',
       'senior web developer', 'sql developer', 'research staff member',
       'sap abap associate consultant', 'associate qa',
       'corporate recruiter', 'project management officer',
       'business systems analyst', 'software programmer',
       'help desk technician', 'sales manager', 'catalog associate',
       'assistant store manager', 'software engg', 'it developer',
       'apprentice', 'business consultant', 'controls engineer',
       'ruby on rails developer', 'risk consultant', 'account manager',
       'professor', 'assistant administrator', 'civil engineer',
       'educator', 'service manager', 'teradata dba',
       'full-time loss prevention associate', 'junior recruiter',
       'associate developer', 'assistant electrical engineer',
       'shift engineer', 'dotnet developer', 'rf/dt engineer',
       'human resources analyst', 'software test engineerte',
       'junior .net developer', 'java trainee', 'maintenance supervisor',
       'r&d engineer', 'front end developer', 'engineer-hws',
       'operations engineer', 'senior research fellow',
       'web designer and joomla administrator',
       'enterprise solutions developer',
       'information technology specialist', 'site engineer',
       'graduate trainee engineer', 'quality assurance analyst',
       'cnc programmer', 'financial analyst', 'system engineer trainee',
       'sap mm consultant', 'assistant system engineer trainee',
       'qa trainee', 'teradata developer', 'hr executive',
       'senior programmer', 'software test engineer (etl)',
       'associate software engg', 'supply chain analyst', 'sales trainer',
       'software executive', 'team leader',
       'assistant system engineer - trainee', 'seo analyst',
       'risk investigator', 'executive administrative assistant',
       'program manager', 'r & d', 'sap functional consultant',
       'website developer/tester', 'software designer',
       'sales coordinator', 'qa engineer', 'aircraft technician',
       'customer care executive', 'senior test engineer',
       'program analyst trainee', 'electrical controls engineer',
       'trainee decision scientist', 'editor', 'bss engineer', 'dba',
       'software eng', 'computer faculty', 'recruitment associate',
       'logistics executive', 'quality consultant',
       'senior sales executive', 'db2 dba', 'test technician',
       'it operations associate', 'software engineering associate',
       'research scientist', 'jr. software developer'], dtype=object)

d['Designation'].str.upper()

ID
203097         SENIOR QUALITY ENGINEER
579905               ASSISTANT MANAGER
810601                SYSTEMS ENGINEER
267447        SENIOR SOFTWARE ENGINEER
343523                             GET
                      ...             
407755                         MANAGER
575154               SOFTWARE ENGINEER
216598                TECHNICAL WRITER
919755     ASSOCIATE SOFTWARE ENGINEER
1037308             SOFTWARE DEVELOPER
Name: Designation, Length: 5498, dtype: object

d.head(2)

d['10percentage'].mean()

78.05070025463795

d['Salary'].mean()

305605.49290651147

d.describe()

d['Designation'] = d['Designation'].astype(str)

Pandas 1.0 introduces a new datatype specific to string data which is StringDtype.
As of now, we can still use object or StringDtype to store strings but in the future, we may be required to only use StringDtype.
One important thing to note here is that object datatype is still the default datatype for strings
Covert a column to string string datatype
- df['points'] = df['points'].astype(str)
Convert multiple columns to string type
- df[['points', 'assists']] = df[['points', 'assists']].astype(str)

df10 = d.sample(10)

df10

def sal_low_red(x):
    color = 'red' if x < 200000 else 'blue'
    return "color:" + color

work with single column in a dataframe¶

df10.style.bar(subset = ['Salary'])

work with one column as single column¶

df10[['Salary']].style.bar()

df10.style.bar(subset = ['Salary'], color = 'blue')

df10[['Salary']].style.bar(color='blue')

def gender_color(x):
    color = "red" if x == "M" else ""
    return "color:" + color

applying function on Gender col¶

df10.style.applymap(gender_color)

df10[['10percentage']].style.highlight_max(color='red').highlight_min(color='green')

For every cell in the DataFrame, if the value is less than 6 then we will highlight the cell with red color, otherwise with blue color.¶

link: https://www.geeksforgeeks.org/highlight-pandas-dataframes-specific-columns-using-applymap/?ref=rp

Write a function to find the max value and make it bold¶

apply() is used to apply a function along an axis or column of the DataFrame or on values of Series.
applymap() is used to apply a function to each element in a DataFrame.
map() is used to substitute each value in a Series with another value

# importing pandas as pd
import pandas as pd

# creating the dataframe
df = pd.DataFrame({"A" : [14, 4, 5, 4, 1],
				"B" : [5, 2, 54, 3, 2],
				"C" : [20, 20, 7, 3, 8],
				"D" : [14, 3, 6, 2, 6]})

print("Original DataFrame :")
display(df)

Original DataFrame :

# function definition
def highlight_cols(s):
    color = 'red' if s < 6 else 'blue'
    return 'background-color: % s' % color
  
# highlighting the cells
display(df.style.applymap(highlight_cols))

# function definition
def highlight_cols(s):
    color = "red" if s < 10 else "blue"
    # return 'background-color: % s' % 'green' if s < 10 else "blue"
    return "color:" + color
    # return 'background-color:' + color
  
# highlighting the cells
display(df.style.applymap(highlight_cols, 
                          subset = pd.IndexSlice[:, ['B', 'C']]))

df10.head(2)

apply color code for multiple colums with IndexSlice Option¶

# function definition
def highlight_cols(s):
    color = "red" if s <= 70 else "green"
    # return 'background-color: % s' % 'green'
    # return "color:" + color
    return 'background-color: ' + color
  
# highlighting the cells
display(df10.style.applymap(highlight_cols, 
                          subset = pd.IndexSlice[:, ['10percentage', '12percentage']]))

apply color code for one column¶

def highlight_cols(s):
    color = "red" if s <= 70 else "green"
    return 'background-color: ' + color

display(df10.style.applymap(highlight_cols, subset = pd.IndexSlice[:, ['12percentage']]))

df10.style.applymap(highlight_cols, subset = pd.IndexSlice[:, ['10percentage']]).bar(color='blue')

apply style with bar only for two cols with SUBSET option¶

df10.style.bar(subset=['10percentage','12percentage', 'English', 'Logical', 'Quant'], color="blue")

## highlight min and max values

df10.style.highlight_max(subset=['10percentage', '12percentage'], color='red')

df10.style.highlight_max(subset=['10percentage', '12percentage'], color='red').highlight_min(subset = ['10percentage', "12percentage"], color='blue')

df10.style.background_gradient(cmap = 'red')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/IPython/core/formatters.py in __call__(self, obj)
    332                 pass
    333             else:
--> 334                 return printer(obj)
    335             # Finally look for special method names
    336             method = get_real_method(obj, self.print_method)

/usr/local/lib/python3.7/dist-packages/google/colab/_reprs.py in new_formatter(dataframe)
     86 
     87   def new_formatter(dataframe):
---> 88     return dataframe.set_table_attributes('class="dataframe"')._repr_html_()  # pylint: disable=protected-access
     89 
     90   _original_df_formatters[key] = formatters[key].for_type_by_name(

/usr/local/lib/python3.7/dist-packages/pandas/io/formats/style.py in _repr_html_(self)
    214         Hooks into Jupyter notebook rich display system.
    215         """
--> 216         return self.render()
    217 
    218     def render(

/usr/local/lib/python3.7/dist-packages/pandas/io/formats/style.py in render(self, sparse_index, sparse_columns, **kwargs)
    270         if sparse_columns is None:
    271             sparse_columns = get_option("styler.sparse.columns")
--> 272         return self._render_html(sparse_index, sparse_columns, **kwargs)
    273 
    274     def set_tooltips(

/usr/local/lib/python3.7/dist-packages/pandas/io/formats/style_render.py in _render_html(self, sparse_index, sparse_columns, **kwargs)
    119         Generates a dict with necessary kwargs passed to jinja2 template.
    120         """
--> 121         self._compute()
    122         # TODO: namespace all the pandas keys
    123         d = self._translate(sparse_index, sparse_columns)

/usr/local/lib/python3.7/dist-packages/pandas/io/formats/style_render.py in _compute(self)
    158         r = self
    159         for func, args, kwargs in self._todo:
--> 160             r = func(self)(*args, **kwargs)
    161         return r
    162 

/usr/local/lib/python3.7/dist-packages/pandas/io/formats/style.py in _apply(self, func, axis, subset, **kwargs)
   1053         data = self.data.loc[subset]
   1054         if axis is not None:
-> 1055             result = data.apply(func, axis=axis, result_type="expand", **kwargs)
   1056             result.columns = data.columns
   1057         else:

/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py in apply(self, func, axis, raw, result_type, args, **kwargs)
   8738             kwargs=kwargs,
   8739         )
-> 8740         return op.apply()
   8741 
   8742     def applymap(

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in apply(self)
    686             return self.apply_raw()
    687 
--> 688         return self.apply_standard()
    689 
    690     def agg(self):

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in apply_standard(self)
    810 
    811     def apply_standard(self):
--> 812         results, res_index = self.apply_series_generator()
    813 
    814         # wrap results

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in apply_series_generator(self)
    826             for i, v in enumerate(series_gen):
    827                 # ignore SettingWithCopy here in case the user mutates
--> 828                 results[i] = self.f(v)
    829                 if isinstance(results[i], ABCSeries):
    830                     # If we have a view on v, we need to make a copy because

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in f(x)
    129 
    130             def f(x):
--> 131                 return func(x, *args, **kwargs)
    132 
    133         else:

/usr/local/lib/python3.7/dist-packages/pandas/io/formats/style.py in _background_gradient(data, cmap, low, high, text_color_threshold, vmin, vmax, gmap, text_only)
   2816         # extend lower / upper bounds, compresses color range
   2817         norm = colors.Normalize(smin - (rng * low), smax + (rng * high))
-> 2818         rgbas = plt.cm.get_cmap(cmap)(norm(gmap))
   2819 
   2820         def relative_luminance(rgba) -> float:

/usr/local/lib/python3.7/dist-packages/matplotlib/cm.py in get_cmap(name, lut)
    132     if isinstance(name, colors.Colormap):
    133         return name
--> 134     cbook._check_in_list(sorted(cmap_d), name=name)
    135     if lut is None:
    136         return cmap_d[name]

/usr/local/lib/python3.7/dist-packages/matplotlib/cbook/__init__.py in _check_in_list(_values, **kwargs)
   2143             raise ValueError(
   2144                 "{!r} is not a valid value for {}; supported values are {}"
-> 2145                 .format(v, k, ', '.join(map(repr, values))))
   2146 
   2147 

ValueError: 'red' is not a valid value for name; supported values are 'Accent', 'Accent_r', 'Blues', 'Blues_r', 'BrBG', 'BrBG_r', 'BuGn', 'BuGn_r', 'BuPu', 'BuPu_r', 'CMRmap', 'CMRmap_r', 'Dark2', 'Dark2_r', 'GnBu', 'GnBu_r', 'Greens', 'Greens_r', 'Greys', 'Greys_r', 'OrRd', 'OrRd_r', 'Oranges', 'Oranges_r', 'PRGn', 'PRGn_r', 'Paired', 'Paired_r', 'Pastel1', 'Pastel1_r', 'Pastel2', 'Pastel2_r', 'PiYG', 'PiYG_r', 'PuBu', 'PuBuGn', 'PuBuGn_r', 'PuBu_r', 'PuOr', 'PuOr_r', 'PuRd', 'PuRd_r', 'Purples', 'Purples_r', 'RdBu', 'RdBu_r', 'RdGy', 'RdGy_r', 'RdPu', 'RdPu_r', 'RdYlBu', 'RdYlBu_r', 'RdYlGn', 'RdYlGn_r', 'Reds', 'Reds_r', 'Set1', 'Set1_r', 'Set2', 'Set2_r', 'Set3', 'Set3_r', 'Spectral', 'Spectral_r', 'Wistia', 'Wistia_r', 'YlGn', 'YlGnBu', 'YlGnBu_r', 'YlGn_r', 'YlOrBr', 'YlOrBr_r', 'YlOrRd', 'YlOrRd_r', 'afmhot', 'afmhot_r', 'autumn', 'autumn_r', 'binary', 'binary_r', 'bone', 'bone_r', 'brg', 'brg_r', 'bwr', 'bwr_r', 'cividis', 'cividis_r', 'cool', 'cool_r', 'coolwarm', 'coolwarm_r', 'copper', 'copper_r', 'crest', 'crest_r', 'cubehelix', 'cubehelix_r', 'flag', 'flag_r', 'flare', 'flare_r', 'gist_earth', 'gist_earth_r', 'gist_gray', 'gist_gray_r', 'gist_heat', 'gist_heat_r', 'gist_ncar', 'gist_ncar_r', 'gist_rainbow', 'gist_rainbow_r', 'gist_stern', 'gist_stern_r', 'gist_yarg', 'gist_yarg_r', 'gnuplot', 'gnuplot2', 'gnuplot2_r', 'gnuplot_r', 'gray', 'gray_r', 'hot', 'hot_r', 'hsv', 'hsv_r', 'icefire', 'icefire_r', 'inferno', 'inferno_r', 'jet', 'jet_r', 'magma...

<pandas.io.formats.style.Styler at 0x7f53ca4c9850>

df10.style.background_gradient(cmap = 'Blues')

df10.style.background_gradient(cmap = 'Pastel1')

d.groupby('Designation')['Designation'].count()

Designation
.net developer                   48
.net web developer                5
account executive                 4
account manager                   1
admin assistant                   2
                                 ..
web designer and seo              1
web developer                    77
web intern                        1
website developer/tester          2
windows systems administrator     1
Name: Designation, Length: 419, dtype: int64

c = df10.groupby('JobCity')['JobCity'].count()

plt.pie(c, labels = c.index)

([<matplotlib.patches.Wedge at 0x7f53ca96f350>,
  <matplotlib.patches.Wedge at 0x7f53ca96fa10>,
  <matplotlib.patches.Wedge at 0x7f53ca9b5290>,
  <matplotlib.patches.Wedge at 0x7f53ca9b5390>,
  <matplotlib.patches.Wedge at 0x7f53ca9bb4d0>,
  <matplotlib.patches.Wedge at 0x7f53ca9bbd90>,
  <matplotlib.patches.Wedge at 0x7f53ca96d3d0>,
  <matplotlib.patches.Wedge at 0x7f53ca96d050>],
 [Text(1.0461621663333946, 0.3399186987098808, 'Ahmedabad'),
  Text(-5.149471629032507e-08, 1.0999999999999988, 'Bangalore'),
  Text(-1.0461621981588756, 0.3399186007611085, 'Chennai'),
  Text(-1.0461621345079049, -0.3399187966586502, 'Gurgaon'),
  Text(-0.646563681703485, -0.8899187634284573, 'Hyderabad'),
  Text(1.2873679044788556e-07, -1.0999999999999925, 'Pune'),
  Text(0.646563890003987, -0.8899186120892812, 'Trivandrum'),
  Text(1.0461622140716127, -0.3399185517867209, 'noida')])

use semi-colon ";" to supress the running text before graph¶

plt.pie(c, labels = c.index);

plt.pie(c, labels = c.index, autopct = "%.2f%%");

plt.pie(c, labels = c.index, autopct = "%.2f%%", rotatelabels = True);

plt.pie(d.groupby('Designation')['Designation'].count());

plt.pie(d.groupby('Designation')['Designation'].count(), autopct = "%2.f%%", pctdistance = 1.2);

plt.pie(df10.groupby('Designation')['Designation'].count(), autopct="%.2f%%", pctdistance = 0.6, shadow=False, labeldistance = 2.1);

d.head(1)

plt.pie(df10.groupby('Designation')['Designation'].count(), autopct="%.2f%%", pctdistance = 1.2, shadow=False, labeldistance = 2.1, wedgeprops = dict(width=0.3));

plt.pie(df10.groupby('JobCity')['JobCity'].count(), 
        wedgeprops = dict(width = 0.2), 
        autopct = "%.2f%%", 
        shadow=True, 
        pctdistance = 1.2);

Pie chart Parameters¶

(x, explode=None, labels=None, colors=None, autopct=None, pctdistance=0.6, shadow=False, labeldistance=1.1, startangle=None, radius=None, counterclock=True, wedgeprops=None, textprops=None, center=(0, 0), frame=False, rotatelabels=False, *, data=None) -> Any
to convert a pie chart to a donut chart, use wedgeprops property with suitable value
a full circle has a value of 1, and the value may range between 0.1 to 1 ie: wedgeprops = dict(width = 0.2)

c = df10.groupby('JobCity')['JobCity'].count()
plt.pie(c, autopct = "%.2f%%", 
        pctdistance = 1.2, 
        labels = c.index, 
        labeldistance = 1.4, 
        wedgeprops = dict(width = .25));

df10.head(3)

data split¶

d.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 5498 entries, 203097 to 1037308
Data columns (total 37 columns):
 #   Column                 Non-Null Count  Dtype         
---  ------                 --------------  -----         
 0   Salary                 5498 non-null   int64         
 1   DOJ                    5498 non-null   datetime64[ns]
 2   DOL                    5498 non-null   object        
 3   Designation            5498 non-null   object        
 4   JobCity                5498 non-null   object        
 5   Gender                 5498 non-null   object        
 6   DOB                    5498 non-null   datetime64[ns]
 7   10percentage           5498 non-null   float64       
 8   10board                5498 non-null   object        
 9   12graduation           5498 non-null   int64         
 10  12percentage           5498 non-null   float64       
 11  12board                5498 non-null   object        
 12  CollegeID              5498 non-null   int64         
 13  CollegeTier            5498 non-null   int64         
 14  Degree                 5498 non-null   object        
 15  Specialization         5498 non-null   object        
 16  collegeGPA             5498 non-null   float64       
 17  CollegeCityID          5498 non-null   int64         
 18  CollegeCityTier        5498 non-null   int64         
 19  CollegeState           5498 non-null   object        
 20  GraduationYear         5498 non-null   int64         
 21  English                5498 non-null   int64         
 22  Logical                5498 non-null   int64         
 23  Quant                  5498 non-null   int64         
 24  Domain                 5498 non-null   float64       
 25  ComputerProgramming    5498 non-null   int64         
 26  ElectronicsAndSemicon  5498 non-null   int64         
 27  ComputerScience        5498 non-null   int64         
 28  MechanicalEngg         5498 non-null   int64         
 29  ElectricalEngg         5498 non-null   int64         
 30  TelecomEngg            5498 non-null   int64         
 31  CivilEngg              5498 non-null   int64         
 32  conscientiousness      5498 non-null   float64       
 33  agreeableness          5498 non-null   float64       
 34  extraversion           5498 non-null   float64       
 35  nueroticism            5498 non-null   float64       
 36  openess_to_experience  5498 non-null   float64       
dtypes: datetime64[ns](2), float64(9), int64(17), object(9)
memory usage: 1.6+ MB

df_init = d[['Salary', 'DOJ', 'DOL', 'Designation', 'JobCity', 'Gender', 'DOB',
             'CollegeID', 'conscientiousness', 'agreeableness', 'extraversion', 'nueroticism', 'openess_to_experience']]

dfs_init = df_init.sample(1000)

dfs_init.head(2)

df_engg = d[['CollegeID', 'ComputerProgramming', 'ElectronicsAndSemicon', 'ComputerScience', 'MechanicalEngg', 'ElectricalEngg', 'TelecomEngg', 'CivilEngg',  'CollegeState']]

dfs_engg = df_engg.sample(1000)

dfs_engg.head(3)

df_engg.head(2)

df_score = d[['Gender', '10board', '10percentage', '12board', '12graduation', 'Degree',
              'CollegeID', 'CollegeTier', 'CollegeState', 'Specialization', 'English', 'Logical', 'Quant'	]]

df_score.head(2)

df_user = d[['Salary', 'DOJ', 'DOL', 'Designation', 'JobCity', 'Gender', 'DOB']]

dfs_user = df_user.sample(100)

dfs_user.head()

dfs_user
dfs_engg
dfs_init

dfs_user.head(2)

dfs_user.groupby(dfs_user['JobCity']).count()

dfs_user.groupby('JobCity')['JobCity'].count()

JobCity
-1                    12
AM                     1
Bangalore             20
Bhubaneswar            1
Chennai                5
Greater noida          1
Gurgaon                6
Hyderabad              7
Jaipur                 2
Kochi/Cochin           1
Kolkata                2
Lucknow                1
Mangalore              1
Mumbai                 2
Mysore                 3
Nagpur                 2
Neemrana               1
New Delhi              4
Noida                 11
Pune                   7
Sonipat                1
Thiruvananthapuram     1
bangalore              1
chennai                2
delhi                  1
noida                  2
pune                   1
pune                   1
Name: JobCity, dtype: int64

dfs_user['JobCity'] = dfs_user['JobCity'].replace("-1", "Not Available", inplace=True)

dfs_user.groupby('JobCity')['JobCity'].count()

Series([], Name: JobCity, dtype: int64)

c

JobCity
Ahmedabad     1
Bangalore     3
Chennai       1
Gurgaon       1
Hyderabad     1
Pune          1
Trivandrum    1
noida         1
Name: JobCity, dtype: int64

to replace an existing value with another value in JobCity col¶

dfs_user.replace(to_replace = -1, value="Not Available")

sns.barplot(x='Designation', y='Salary', data = dfs_user)

<matplotlib.axes._subplots.AxesSubplot at 0x7f53c92f3490>

d.head(1)

sns.histplot(d['10percentage'])

<matplotlib.axes._subplots.AxesSubplot at 0x7f53c9108dd0>

plt.bar(d.Designation, d.Salary)

<BarContainer object of 5498 artists>

ds100 = d.sample(100)

ds = d.sample(100)

ds.head()

plt.bar(ds.Designation, ds.Salary)

<BarContainer object of 100 artists>

fig = plt.gcf();
fig.set_size_inches(15, 10);
plt.barh(ds.Designation, ds.Salary)

<BarContainer object of 100 artists>

ds.sort_values('Salary')

fig = plt.gcf()
fig.set_size_inches(8 ,8)
plt.bar(ds.Designation, ds.Salary)

<BarContainer object of 100 artists>

fig = plt.gcf()
fig.set_size_inches(10, 8)
dsa = ds.sort_values(by='Salary', ascending=True, kind = "mergesort")
plt.barh(dsa.Designation, dsa.Salary)

<BarContainer object of 100 artists>

dsa = ds.sort_values(by=["Salary", "Designation"])[["Salary", "Designation"]]

fig = plt.gcf()
fig.set_size_inches(8, 8)
plt.barh(dsa.Designation, ds.Salary)

<BarContainer object of 100 artists>

Find the min salary and corresponding Designation¶

dsa[['Salary', 'Designation']].min()

Salary                  85000
Designation    .net developer
dtype: object

d[['Salary', 'Designation']].min()

Salary                  35000
Designation    .net developer
dtype: object

dsa.min()

Salary                  85000
Designation    .net developer
dtype: object

returns min in all the columns in the dataframe¶

ds.min()

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.
  """Entry point for launching an IPython kernel.

Salary                                 85000
DOJ                      2010-04-01 00:00:00
Designation                   .net developer
Gender                                     f
DOB                      1985-02-06 00:00:00
10percentage                            45.0
12graduation                            2002
12percentage                            50.0
CollegeID                                 44
CollegeTier                                1
Degree                           B.Tech/B.E.
Specialization             civil engineering
collegeGPA                              7.56
CollegeCityID                             44
CollegeCityTier                            0
CollegeState                  Andhra Pradesh
GraduationYear                          2010
English                                  205
Logical                                  235
Quant                                    150
Domain                                  -1.0
ComputerProgramming                       -1
ElectronicsAndSemicon                     -1
ComputerScience                           -1
MechanicalEngg                            -1
ElectricalEngg                            -1
TelecomEngg                               -1
CivilEngg                                 -1
conscientiousness                    -3.0448
agreeableness                        -3.9501
extraversion                         -2.7565
nueroticism                          -2.5163
openess_to_experience                -5.6512
dtype: object

gets min values from each row¶

ds.min(axis = 1)

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.
  """Entry point for launching an IPython kernel.

ID
330760   -1.0000
982387   -1.4517
529705   -1.0000
627124   -1.0000
358189   -1.0135
           ...  
942010   -1.0000
668152   -1.0000
42943    -1.5273
335166   -1.0000
536794   -1.0000
Length: 100, dtype: float64

dsa.head()

get the entire row for a max value on a particular column¶

dsa.loc[dsa['Salary'].idxmax()]

Salary                2000000
Designation    technical lead
Name: 803778, dtype: object

ds.loc[ds['Salary'].idxmin()]

Salary                                                       85000
DOJ                                            2012-06-01 00:00:00
DOL                                            2013-04-01 00:00:00
Designation                                      account executive
JobCity                                     Technopark, Trivandrum
Gender                                                           f
DOB                                            1988-08-02 00:00:00
10percentage                                                  77.0
10board                                                       cbse
12graduation                                                  2007
12percentage                                                  70.0
12board                                                       cbse
CollegeID                                                     5442
CollegeTier                                                      2
Degree                                                 B.Tech/B.E.
Specialization           electronics and communication engineering
collegeGPA                                                   69.34
CollegeCityID                                                 5442
CollegeCityTier                                                  0
CollegeState                                                Kerala
GraduationYear                                                2011
English                                                        505
Logical                                                        445
Quant                                                          445
Domain                                                    0.694479
ComputerProgramming                                            365
ElectronicsAndSemicon                                          366
ComputerScience                                                 -1
MechanicalEngg                                                  -1
ElectricalEngg                                                  -1
TelecomEngg                                                    366
CivilEngg                                                       -1
conscientiousness                                           0.9737
agreeableness                                              -0.9033
extraversion                                                0.0914
nueroticism                                                -1.8179
openess_to_experience                                      -1.2354
Name: 308499, dtype: object

dfs_user.head(2)

dfs_user.loc[dfs_user['Salary'].idxmin()]

Salary                          60000
DOJ               2013-03-01 00:00:00
DOL               2014-04-01 00:00:00
Designation    software test engineer
JobCity                          None
Gender                              m
DOB               1989-10-20 00:00:00
Name: 371808, dtype: object

dfs_user.loc[dfs_user['Salary'].idxmax()]

Salary                     1200000
DOJ            2011-02-01 00:00:00
DOL                        present
Designation        design engineer
JobCity                       None
Gender                           m
DOB            1987-10-02 00:00:00
Name: 30706, dtype: object

res = dfs_user.loc[dfs_user['Salary'].idxmax()]

display(res)

Salary                     1200000
DOJ            2011-02-01 00:00:00
DOL                        present
Designation        design engineer
JobCity                       None
Gender                           m
DOB            1987-10-02 00:00:00
Name: 30706, dtype: object

print(res)

Salary                     1200000
DOJ            2011-02-01 00:00:00
DOL                        present
Designation        design engineer
JobCity                       None
Gender                           m
DOB            1987-10-02 00:00:00
Name: 30706, dtype: object

dfs_user['Salary'].mean()

289900.0

dfs_user['Salary'].median()

245000.0

dfs_user['Salary'].mean() / dfs_user["Salary"].median()

1.183265306122449

plt.bar(ds100['Designation'], ds100['Salary'])

<BarContainer object of 100 artists>

ds100.head(1)

ds100['JobCity'] = np.where(ds100['JobCity'] == "-1", "Not available", ds100['JobCity'])

ds100

Example¶

df_ex = pd.DataFrame({'A': [-2, 7, -4, 0], 'B': [-6, -1, 2, -8], 'C': [1, 2, 3, 4]})

df_ex

#it goes through column A, selects where it's negative & replaces with 2, or if it's not negative it puts in the values from column C
df_ex.A = np.where(df_ex.A < 0, 250, df_ex.C)

df_ex

#it goes through column A, selects where it's negative & replaces with 2, or if it's not negative it leaves it as is
df_ex.A = np.where(df_ex.A < 0, 250, df_ex.A)

df_ex

	Salary	10percentage	12graduation	12percentage	CollegeID	CollegeTier	collegeGPA	CollegeCityID	CollegeCityTier	GraduationYear	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
count	5.498000e+03	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	...	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000	5498.000000
mean	3.056055e+05	78.050700	2008.096944	74.597506	5169.293198	1.925973	71.521359	5169.293198	0.294289	2012.246453	...	89.173518	22.979629	17.623136	32.580757	3.042197	-0.037976	0.156622	0.015219	-0.147904	-0.128363
std	2.030102e+05	9.774724	1.636035	10.902039	4787.707246	0.261839	8.328995	4787.707246	0.455764	27.174495	...	174.314470	98.511684	90.694107	105.358134	38.560043	1.026689	0.919777	0.943009	1.008903	0.982055
min	3.500000e+04	43.000000	1995.000000	40.000000	2.000000	1.000000	6.450000	2.000000	0.000000	0.000000	...	-1.000000	-1.000000	-1.000000	-1.000000	-1.000000	-4.126700	-5.781600	-4.600900	-2.643000	-7.375700
25%	1.800000e+05	72.000000	2007.000000	66.400000	513.000000	2.000000	66.700000	513.000000	0.000000	2012.000000	...	-1.000000	-1.000000	-1.000000	-1.000000	-1.000000	-0.726400	-0.287100	-0.604800	-0.868200	-0.669200
50%	3.000000e+05	79.600000	2008.000000	74.530000	3879.000000	2.000000	71.830000	3879.000000	0.000000	2013.000000	...	-1.000000	-1.000000	-1.000000	-1.000000	-1.000000	0.046400	0.212400	0.091400	-0.172700	-0.050600
75%	3.700000e+05	85.615000	2009.000000	82.800000	8816.250000	2.000000	76.400000	8816.250000	1.000000	2014.000000	...	-1.000000	-1.000000	-1.000000	-1.000000	-1.000000	0.702700	0.812800	0.672000	0.526200	0.502400
max	4.000000e+06	97.760000	2013.000000	98.700000	18409.000000	2.000000	99.930000	18409.000000	1.000000	2017.000000	...	746.000000	653.000000	676.000000	553.000000	548.000000	1.995300	1.904800	2.535400	3.352500	1.822400

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
902841	430000	2014-05-01	2014-08-01 00:00:00	software engineer	Hyderabad	m	1992-05-19	83.00	state board	2010	...	-1	-1	-1	-1	-1	-0.7335	-0.4536	0.1637	1.0333	-0.2859
89357	225000	2011-02-01	2011-07-01 00:00:00	technical support engineer	Bangalore	m	1989-01-05	69.00	sslc	2006	...	-1	-1	-1	-1	-1	1.4374	-1.2153	-0.6343	-0.2902	-2.0253
984851	320000	2015-03-01	2015-05-01 00:00:00	system engineer	Ahmedabad	m	1993-08-20	78.17	state board	2010	...	-1	-1	676	-1	-1	1.1336	0.3789	0.1637	-0.7415	-0.6692
1129408	250000	2013-06-01	present	system engineer	Chennai	m	1990-04-19	69.00	state board	2009	...	-1	-1	-1	-1	-1	0.1282	0.5454	-0.6048	0.0192	-1.0524
1088496	120000	2014-08-01	present	junior software engineer	Trivandrum	m	1990-11-16	75.00	cbse	2009	...	-1	-1	-1	-1	-1	-0.4463	0.0459	-0.7585	-1.2486	-0.4776
687711	300000	2014-06-01	present	software engineer	noida	m	1990-10-31	83.20	cbse	2009	...	438	-1	-1	-1	-1	-1.4517	0.2124	0.1637	-0.7415	-0.8608
994256	340000	2014-04-01	2015-04-01 00:00:00	web application developer	Bangalore	m	1991-12-13	74.00	state board	2009	...	-1	-1	-1	-1	-1	0.5591	0.0459	0.6248	0.5262	1.6302
109166	380000	2012-02-01	2014-08-01 00:00:00	software engineer	Pune	f	1989-09-03	79.83	gshseb	2006	...	-1	-1	-1	-1	-1	0.2009	0.0328	-0.0537	-1.4653	0.1864
1193139	325000	2014-08-01	2015-04-01 00:00:00	software engineer	Bangalore	m	1992-06-25	71.84	state board	2010	...	-1	-1	-1	-1	-1	0.1282	0.2124	-0.9122	1.0333	-0.0943
1226693	350000	2015-02-01	present	front end developer	Gurgaon	f	1993-08-12	92.00	cbse	2011	...	-1	-1	-1	-1	-1	-1.1644	0.7119	-0.6048	-0.3612	0.6721

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	12percentage	12board	CollegeID	CollegeTier	Degree	Specialization	collegeGPA	CollegeCityID	CollegeCityTier	CollegeState	GraduationYear	English	Logical	Quant	Domain	ComputerProgramming	ElectronicsAndSemicon	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
902841	430000	2014-05-01 00:00:00	2014-08-01 00:00:00	software engineer	Hyderabad	m	1992-05-19 00:00:00	83.000000	state board	2010	82.000000	state board	9775	2	B.Tech/B.E.	computer science & engineering	71.000000	9775	1	Telangana	2014	425	465	470	-1.000000	-1	-1	-1	-1	-1	-1	-1	-0.733500	-0.453600	0.163700	1.033300	-0.285900
89357	225000	2011-02-01 00:00:00	2011-07-01 00:00:00	technical support engineer	Bangalore	m	1989-01-05 00:00:00	69.000000	sslc	2006	50.000000	puc	1648	2	B.Tech/B.E.	information technology	60.000000	1648	1	Karnataka	2010	404	375	395	0.488348	405	-1	-1	-1	-1	-1	-1	1.437400	-1.215300	-0.634300	-0.290200	-2.025300
984851	320000	2015-03-01 00:00:00	2015-05-01 00:00:00	system engineer	Ahmedabad	m	1993-08-20 00:00:00	78.170000	state board	2010	77.850000	state board	4948	2	B.Tech/B.E.	electrical engineering	76.850000	4948	1	Rajasthan	2014	675	495	545	0.997698	-1	-1	-1	-1	676	-1	-1	1.133600	0.378900	0.163700	-0.741500	-0.669200
1129408	250000	2013-06-01 00:00:00	present	system engineer	Chennai	m	1990-04-19 00:00:00	69.000000	state board	2009	61.300000	state board	5039	2	B.Tech/B.E.	electronics and communication engineering	69.000000	5039	0	Andhra Pradesh	2013	430	425	295	0.338786	175	292	-1	-1	-1	-1	-1	0.128200	0.545400	-0.604800	0.019200	-1.052400
1088496	120000	2014-08-01 00:00:00	present	junior software engineer	Trivandrum	m	1990-11-16 00:00:00	75.000000	cbse	2009	80.000000	state board	10361	2	B.Tech/B.E.	electronics and communication engineering	60.850000	10361	0	Kerala	2013	570	580	750	-1.000000	495	-1	-1	-1	-1	-1	-1	-0.446300	0.045900	-0.758500	-1.248600	-0.477600
687711	300000	2014-06-01 00:00:00	present	software engineer	noida	m	1990-10-31 00:00:00	83.200000	cbse	2009	67.000000	state board	7814	2	B.Tech/B.E.	computer science & engineering	70.700000	7814	0	Orissa	2013	565	615	445	0.744758	295	-1	438	-1	-1	-1	-1	-1.451700	0.212400	0.163700	-0.741500	-0.860800
994256	340000	2014-04-01 00:00:00	2015-04-01 00:00:00	web application developer	Bangalore	m	1991-12-13 00:00:00	74.000000	state board	2009	78.000000	state board	10389	2	B.Tech/B.E.	electronics & telecommunications	73.720000	10389	0	Madhya Pradesh	2013	405	470	585	0.783304	505	388	-1	-1	-1	-1	-1	0.559100	0.045900	0.624800	0.526200	1.630200
109166	380000	2012-02-01 00:00:00	2014-08-01 00:00:00	software engineer	Pune	f	1989-09-03 00:00:00	79.830000	gshseb	2006	68.330000	gshseb	988	2	B.Tech/B.E.	electronics and communication engineering	68.740000	988	0	Gujarat	2010	435	605	685	0.824666	-1	400	-1	-1	-1	-1	-1	0.200900	0.032800	-0.053700	-1.465300	0.186400
1193139	325000	2014-08-01 00:00:00	2015-04-01 00:00:00	software engineer	Bangalore	m	1992-06-25 00:00:00	71.840000	state board	2010	66.830000	state board	3770	2	B.Tech/B.E.	computer science & engineering	70.350000	3770	0	Karnataka	2016	640	615	585	0.974396	615	-1	-1	-1	-1	-1	-1	0.128200	0.212400	-0.912200	1.033300	-0.094300
1226693	350000	2015-02-01 00:00:00	present	front end developer	Gurgaon	f	1993-08-12 00:00:00	92.000000	cbse	2011	85.600000	cbse	115	2	B.Tech/B.E.	computer science & engineering	91.000000	115	0	Punjab	2015	535	480	605	-1.000000	-1	-1	-1	-1	-1	-1	-1	-1.164400	0.711900	-0.604800	-0.361200	0.672100

	Salary
ID
902841	430000
89357	225000
984851	320000
1129408	250000
1088496	120000
687711	300000
994256	340000
109166	380000
1193139	325000
1226693	350000

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	12percentage	12board	CollegeID	CollegeTier	Degree	Specialization	collegeGPA	CollegeCityID	CollegeCityTier	CollegeState	GraduationYear	English	Logical	Quant	Domain	ComputerProgramming	ElectronicsAndSemicon	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
902841	430000	2014-05-01 00:00:00	2014-08-01 00:00:00	software engineer	Hyderabad	m	1992-05-19 00:00:00	83.000000	state board	2010	82.000000	state board	9775	2	B.Tech/B.E.	computer science & engineering	71.000000	9775	1	Telangana	2014	425	465	470	-1.000000	-1	-1	-1	-1	-1	-1	-1	-0.733500	-0.453600	0.163700	1.033300	-0.285900
89357	225000	2011-02-01 00:00:00	2011-07-01 00:00:00	technical support engineer	Bangalore	m	1989-01-05 00:00:00	69.000000	sslc	2006	50.000000	puc	1648	2	B.Tech/B.E.	information technology	60.000000	1648	1	Karnataka	2010	404	375	395	0.488348	405	-1	-1	-1	-1	-1	-1	1.437400	-1.215300	-0.634300	-0.290200	-2.025300
984851	320000	2015-03-01 00:00:00	2015-05-01 00:00:00	system engineer	Ahmedabad	m	1993-08-20 00:00:00	78.170000	state board	2010	77.850000	state board	4948	2	B.Tech/B.E.	electrical engineering	76.850000	4948	1	Rajasthan	2014	675	495	545	0.997698	-1	-1	-1	-1	676	-1	-1	1.133600	0.378900	0.163700	-0.741500	-0.669200
1129408	250000	2013-06-01 00:00:00	present	system engineer	Chennai	m	1990-04-19 00:00:00	69.000000	state board	2009	61.300000	state board	5039	2	B.Tech/B.E.	electronics and communication engineering	69.000000	5039	0	Andhra Pradesh	2013	430	425	295	0.338786	175	292	-1	-1	-1	-1	-1	0.128200	0.545400	-0.604800	0.019200	-1.052400
1088496	120000	2014-08-01 00:00:00	present	junior software engineer	Trivandrum	m	1990-11-16 00:00:00	75.000000	cbse	2009	80.000000	state board	10361	2	B.Tech/B.E.	electronics and communication engineering	60.850000	10361	0	Kerala	2013	570	580	750	-1.000000	495	-1	-1	-1	-1	-1	-1	-0.446300	0.045900	-0.758500	-1.248600	-0.477600
687711	300000	2014-06-01 00:00:00	present	software engineer	noida	m	1990-10-31 00:00:00	83.200000	cbse	2009	67.000000	state board	7814	2	B.Tech/B.E.	computer science & engineering	70.700000	7814	0	Orissa	2013	565	615	445	0.744758	295	-1	438	-1	-1	-1	-1	-1.451700	0.212400	0.163700	-0.741500	-0.860800
994256	340000	2014-04-01 00:00:00	2015-04-01 00:00:00	web application developer	Bangalore	m	1991-12-13 00:00:00	74.000000	state board	2009	78.000000	state board	10389	2	B.Tech/B.E.	electronics & telecommunications	73.720000	10389	0	Madhya Pradesh	2013	405	470	585	0.783304	505	388	-1	-1	-1	-1	-1	0.559100	0.045900	0.624800	0.526200	1.630200
109166	380000	2012-02-01 00:00:00	2014-08-01 00:00:00	software engineer	Pune	f	1989-09-03 00:00:00	79.830000	gshseb	2006	68.330000	gshseb	988	2	B.Tech/B.E.	electronics and communication engineering	68.740000	988	0	Gujarat	2010	435	605	685	0.824666	-1	400	-1	-1	-1	-1	-1	0.200900	0.032800	-0.053700	-1.465300	0.186400
1193139	325000	2014-08-01 00:00:00	2015-04-01 00:00:00	software engineer	Bangalore	m	1992-06-25 00:00:00	71.840000	state board	2010	66.830000	state board	3770	2	B.Tech/B.E.	computer science & engineering	70.350000	3770	0	Karnataka	2016	640	615	585	0.974396	615	-1	-1	-1	-1	-1	-1	0.128200	0.212400	-0.912200	1.033300	-0.094300
1226693	350000	2015-02-01 00:00:00	present	front end developer	Gurgaon	f	1993-08-12 00:00:00	92.000000	cbse	2011	85.600000	cbse	115	2	B.Tech/B.E.	computer science & engineering	91.000000	115	0	Punjab	2015	535	480	605	-1.000000	-1	-1	-1	-1	-1	-1	-1	-1.164400	0.711900	-0.604800	-0.361200	0.672100

Consulting - Quality

HomeWork: Ameo with Pandas Visualisations

Homework - ameo15 dataset¶

work with single column in a dataframe¶

work with one column as single column¶

applying function on Gender col¶

For every cell in the DataFrame, if the value is less than 6 then we will highlight the cell with red color, otherwise with blue color.¶

Write a function to find the max value and make it bold¶

apply color code for multiple colums with IndexSlice Option¶

apply color code for one column¶

apply style with bar only for two cols with SUBSET option¶

use semi-colon ";" to supress the running text before graph¶

Pie chart Parameters¶

data split¶

to replace an existing value with another value in JobCity col¶

Find the min salary and corresponding Designation¶

returns min in all the columns in the dataframe¶

gets min values from each row¶

get the entire row for a max value on a particular column¶

Example¶

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
203097	420000	2012-06-01	present	senior quality engineer	Bangalore	f	1990-02-19	84.3	board ofsecondary education,ap	2007	...	-1	-1	-1	-1	-1	0.9737	0.8128	0.5269	1.35490	-0.4455
579905	500000	2013-09-01	present	assistant manager	Indore	m	1989-10-04	85.4	cbse	2007	...	-1	-1	-1	-1	-1	-0.7335	0.3789	1.2396	-0.10760	0.8637
810601	325000	2014-06-01	present	systems engineer	Chennai	f	1992-08-03	85.0	cbse	2010	...	-1	-1	-1	-1	-1	0.2718	1.7109	0.1637	-0.86820	0.6721
267447	1100000	2011-07-01	present	senior software engineer	Gurgaon	m	1989-12-05	85.6	cbse	2007	...	-1	-1	-1	-1	-1	0.0464	0.3448	-0.3440	-0.40780	-0.9194
343523	200000	2014-03-01	2015-03-01 00:00:00	get	Manesar	m	1991-02-27	78.0	cbse	2008	...	-1	-1	-1	-1	-1	-0.8810	-0.2793	-1.0697	0.09163	-0.1295

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	CollegeID	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
796983	415000	2014-06-01	present	assistant manager	PATNA	m	1993-01-20	11848	-1.3080	0.3789	-1.6807	-1.24860	-0.4776
342646	180000	2014-03-01	2014-08-01 00:00:00	software developer	-1	m	1990-09-06	2563	-0.4173	0.5008	0.1640	-0.87777	-0.2875

	CollegeID	ComputerProgramming	ElectronicsAndSemicon	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	CollegeState
ID
693149	272	515	433	-1	-1	-1	-1	-1	Punjab
279776	51	525	-1	-1	-1	-1	-1	-1	Uttar Pradesh
335701	3174	-1	400	-1	-1	-1	313	-1	Andhra Pradesh

	CollegeID	ComputerProgramming	ElectronicsAndSemicon	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	CollegeState
ID
203097	1141	445	-1	-1	-1	-1	-1	-1	Andhra Pradesh
579905	5807	-1	466	-1	-1	-1	-1	-1	Madhya Pradesh

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB
ID
53722	460000	2010-07-01	present	senior software engineer	Pune	m	1988-04-01
87369	400000	2013-02-01	present	senior software engineer	Kolkata	m	1988-07-26
51320	545000	2011-03-01	2015-05-01 00:00:00	technical lead	Bangalore	m	1988-04-17
752121	300000	2014-09-01	present	software developer	Bangalore	m	1988-09-03
909904	345000	2014-12-01	2015-05-01 00:00:00	network engineer	Bangalore	m	1993-06-30

	Salary	DOJ	DOL	Designation	Gender	DOB
JobCity
-1	12	12	12	12	12	12
AM	1	1	1	1	1	1
Bangalore	20	20	20	20	20	20
Bhubaneswar	1	1	1	1	1	1
Chennai	5	5	5	5	5	5
Greater noida	1	1	1	1	1	1
Gurgaon	6	6	6	6	6	6
Hyderabad	7	7	7	7	7	7
Jaipur	2	2	2	2	2	2
Kochi/Cochin	1	1	1	1	1	1
Kolkata	2	2	2	2	2	2
Lucknow	1	1	1	1	1	1
Mangalore	1	1	1	1	1	1
Mumbai	2	2	2	2	2	2
Mysore	3	3	3	3	3	3
Nagpur	2	2	2	2	2	2
Neemrana	1	1	1	1	1	1
New Delhi	4	4	4	4	4	4
Noida	11	11	11	11	11	11
Pune	7	7	7	7	7	7
Sonipat	1	1	1	1	1	1
Thiruvananthapuram	1	1	1	1	1	1
bangalore	1	1	1	1	1	1
chennai	2	2	2	2	2	2
delhi	1	1	1	1	1	1
noida	2	2	2	2	2	2
pune	1	1	1	1	1	1
pune	1	1	1	1	1	1

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
330760	240000	2013-09-01	2014-12-01 00:00:00	sales management trainee	Pune	m	1991-06-24	90.5	andhra pradesh board of secondary education	2008	...	-1	-1	-1	-1	-1	1.1283	0.3448	0.6720	-0.2902	-0.0506
982387	325000	2010-09-01	2012-08-01 00:00:00	software engineer	Mumbai	m	1993-02-06	63.5	cbse	2010	...	376	-1	-1	-1	-1	-1.4517	-0.2871	0.3174	0.2727	0.2889
529705	330000	2014-01-01	present	software engineer	Chennai	m	1990-06-10	83.3	indian certificate for secondary education	2008	...	-1	-1	-1	-1	-1	0.0464	0.6178	-0.0537	-0.2902	-0.2875
627124	500000	2013-08-01	present	software developer	Banglore	m	1992-10-23	87.0	cbse	2009	...	-1	-1	-1	-1	-1	0.2718	0.3789	-0.7585	-0.6147	0.0973
358189	345000	2013-07-01	present	software engineer	Pune	m	1989-11-20	74.8	cbse	2007	...	-1	-1	-1	-1	-1	-1.0135	-0.2793	-0.1988	0.7493	-0.2875

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
1042501	85000	2014-08-01	2015-04-01 00:00:00	quality consultant	Kolkata	f	1991-11-23	72.5	state board	2009	...	-1	-1	-1	-1	-1	1.2772	1.5444	0.9322	-1.1218	0.8637
308499	85000	2012-06-01	2013-04-01 00:00:00	account executive	Technopark, Trivandrum	f	1988-08-02	77.0	cbse	2007	...	-1	-1	-1	366	-1	0.9737	-0.9033	0.0914	-1.8179	-1.2354
288761	95000	2011-07-01	2012-02-01 00:00:00	design engineer	Ernakulam	m	1988-09-15	92.0	kerala state board	2007	...	-1	366	-1	-1	-1	0.8192	-0.2793	-0.1988	-0.6428	0.0284
505831	100000	2012-05-01	2012-09-01 00:00:00	software developer	-1	f	1990-03-15	75.4	central board of secondary education	2008	...	-1	-1	-1	-1	-1	-0.1855	0.9688	-0.1988	1.2374	0.1864
215660	105000	2014-08-01	2015-04-01 00:00:00	java software engineer	Kolkata	m	1989-05-27	69.2	jharkhand academic council	2007	...	-1	-1	-1	233	-1	0.2009	-0.4353	-0.0537	1.1199	0.3444
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
35716	600000	2012-01-01	present	software test engineer	Bangalore	m	1988-09-18	90.0	cbse	2006	...	-1	-1	-1	-1	-1	-0.1082	1.1248	0.0914	-0.8778	-0.2875
1091134	655000	2012-06-01	present	technical consultant	Mumbai	m	1991-02-10	70.0	cbse	2009	...	500	-1	-1	-1	-1	-2.1698	-1.4526	0.6248	1.5404	0.0973
796197	800000	2014-07-01	2015-04-01 00:00:00	software engineer	Bangalore	f	1993-01-11	93.0	cbse	2010	...	500	-1	-1	-1	-1	0.2718	0.5454	-1.2196	-1.5021	-1.2440
42943	1000000	2010-09-01	present	assistant manager	Vadodara	m	1988-05-03	86.0	gseb	2006	...	-1	446	-1	-1	-1	0.9737	-1.5273	0.6720	-0.0552	-1.2354
803778	2000000	2013-07-01	2014-10-01 00:00:00	technical lead	Pune	m	1992-04-24	69.5	state board	2008	...	-1	-1	-1	-1	-1	0.5591	1.0449	1.2396	0.3995	1.0554

	Salary	DOJ	DOL	Designation	JobCity	Gender	DOB	10percentage	10board	12graduation	...	ComputerScience	MechanicalEngg	ElectricalEngg	TelecomEngg	CivilEngg	conscientiousness	agreeableness	extraversion	nueroticism	openess_to_experience
ID
249086	240000	2014-01-01	2014-03-01 00:00:00	sales associate	-1	f	1989-06-01	75.0	icse	2007	...	-1	340	-1	-1	-1	-0.1082	0.6568	-0.6343	0.1798	0.5024