diff --git a/Analysis.ipynb b/Analysis.ipynb index f0bf213..29812cf 100644 --- a/Analysis.ipynb +++ b/Analysis.ipynb @@ -1000,7 +1000,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### **DEMOGRAPHIC ANALYSIS**\n", + "#### **DEMOGRAPHIC ANALYSIS**\n", "\n", "Firstly, we will analyse the **Demographic** to get an overview of the respondents background. This initial analysis will show us how descriptive the survey is of the worldwide community. This might reveal the existence of biases if any.\n" ] @@ -1009,7 +1009,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Gender Distribution**\n", + "#### **I) Gender Distribution**\n", "\n", "\n", "---------\n" @@ -1085,7 +1085,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Country-wise Distribution**\n", + "#### **II) Country-wise Distribution**\n", "------------------------\n", "\n", "Here, we analysze the overall geographical distribution of the Computer Science Community" @@ -1166,7 +1166,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Percentage of respondants from english speaking countries**\n", + "#### **+ Percentage of respondants from english speaking countries**\n", "\n", "We test our hypthesis that language could have been the reason for lesser partcipation from Non-English speaking countries.For this purpose we use `country_lang.xlsx` made using [this link](https://github.com/JovianML/opendatasets/blob/master/data/countries-languages-spoken/countries-languages.csv). The excel contains two columns `Country` and `Languages Spoken`.\n", "\n", @@ -1238,7 +1238,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Gender-wise geographical distribution of the Computer Science Community**\n", + "#### **+ Gender-wise geographical distribution of the Computer Science Community**\n", "\n", "Here, we compare and the total number of Women respondents from a specific country to the total number of women Respondents. We do a similar analysis for men. We get a genderwise geographical distribution of Computer Science community.\n", "\n", @@ -1347,9 +1347,7 @@ "axes[1].pie(men_dist.values, labels = men_dist.index, autopct='%1.2f%%',pctdistance= 0.8, labeldistance=1.05, radius = 2);\n", "axes[1].set_title('Country-wise distribution of Men in Computer Science\\n\\n\\n\\n\\n', pad = 10);\n", "\n", - "fig.subplots_adjust(wspace = 2);\n", - "\n", - "\n" + "fig.subplots_adjust(wspace = 2);" ] }, { @@ -1365,7 +1363,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Age Distribution**\n", + "#### **III) Age Distribution**\n", "-----------------\n" ] }, @@ -1426,7 +1424,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Education Level**\n", + "#### **IV) Education Level**\n", "--------" ] }, @@ -1499,6 +1497,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "\n", "#### **Checking genderwise Highest Level of Formal Education**" ] }, @@ -1506,7 +1505,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **_Graphical_**" + "#### **_1. Graphical_**" ] }, { @@ -1547,7 +1546,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **_Mathematical_**\n", + "#### **_2. Mathematical_**\n", "\n", "We use ratio as the metric to compare responses" ] @@ -1603,7 +1602,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Employment Background**\n", + "#### **V) Employment Background**\n", "----------" ] }, @@ -1919,14 +1918,14 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "### **PROGRAMMING SKILLS**\n" + "#### **PROGRAMMING SKILLS**\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "#### **Programming Languages**\n", + "#### **I) Programming Languages**\n", "________" ] }, @@ -1935,7 +1934,7 @@ "metadata": {}, "source": [ "\n", - "#### **Languages worked with**\n", + "#### **a) Languages worked with**\n", "\n", "Respondents were asked to select all the programming languages they have worked with in the past. The rows in the `LanguageHaveWorkedWith` column contains value seperated by `;`. For this purpose we define a function which takes the column series as input and returns a dataframe with each seperate option as a column. The selected options for each response (each row) is marked as `True`." ] @@ -2015,8 +2014,8 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "-----\n", - "#### **Languages want to work with**" + "\n", + "#### **b) Languages want to work with**" ] }, { @@ -2067,6 +2066,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "---------\n", "## **Questioning and Answering using Data**" ] }, @@ -2371,6 +2371,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "---------\n", "#### ***Q. What is the Average compensation of each Job role?***" ] }, @@ -2507,6 +2508,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "----------\n", "#### ***Q. How does the country wise compensation vary? Is their a parity of compensation between genders?***" ] }, @@ -2611,6 +2613,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "-----------\n", "#### ***Q. Are younger people more open about their sexuality.***" ] }, @@ -2783,7 +2786,9 @@ "\n", "The higher participation can be explained by the growing acceptability and inclusivity for the queer community. Major iniatives have been launched to make spaces more welcoming of the community. \n", "\n", - "This is a sign of socioeconomic growth in the computer science domain." + "This is a sign of socioeconomic growth in the computer science domain.\n", + "\n", + "---------\n" ] } ],