The sour gas reservoir of interest contains high H2S. Elemental sulphur (S8) dissolved in sour gas, precipitated, and deposited in surface facilities when the pressure and temperature are decreasing in the production process. Sulphur deposition has thus formed gas flow restrictions, increasing the back pressure on well head and increasing surface processing pressure closer to the setting point of Pressure Safety Valve (PSV). This requires a real time pressure management that the pressure has closely been monitored to ensure not to trigger the PSV to open, so that the well will not be shut in and sour gas will not vent to the flare stack. The normal practice is that operators will lower the well production rate to manage the pressure or to clean the sulphur deposition in the surface pipeline and valves using specific chemicals to dissolve the sulphur layer adhered to the inside wall of the surface facilities, which leads to several days of production loss. As a result, sulphur deposition has had a negative impact on daily production and lower production reliability due to uncertainty of timing and frequency of the chemical cleaning. Data science with Python has been applied to analyze the impact factors of sulfur deposition on surface pipeline network, so that the timing of reaching PSV setting pressure can be forecasted and the frequency of chemical cleaning can be optimized, resulting in operational cost savings, less production loss, and lower operational risks to workforce. Mature data science technology is fit for this analysis, such as data cleaning, basic statistics, time series analysis, regression, trees, unsupervised machine learning, etc., and the most advanced packages include ARIMA, Random Forests and XGboost.